< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2207 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.1483. Min Act: -0.1700

Data Index: 5124061 (Open Web Text)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.1236. Min Act: -0.1700

Data Index: 3946956 (Open Web Text)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.1160. Min Act: -0.1700

Data Index: 7869490 (Open Web Text)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.1200. Min Act: -0.1700

Data Index: 2469597 (Open Web Text)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.1123. Min Act: -0.1700

Data Index: 7665850 (Open Web Text)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.0938. Min Act: -0.1700

Data Index: 6599040 (Open Web Text)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.1070. Min Act: -0.1700

Data Index: 8355141 (Open Web Text)

Max Activating Token Index: 497

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.1041. Min Act: -0.1700

Data Index: 3707502 (Open Web Text)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.1003. Min Act: -0.1700

Data Index: 3479334 (Open Web Text)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.1050. Min Act: -0.1700

Data Index: 4544465 (Open Web Text)

Max Activating Token Index: 622

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.0891. Min Act: -0.1700

Data Index: 2371778 (Open Web Text)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.1081. Min Act: -0.1700

Data Index: 4957108 (Open Web Text)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.0989. Min Act: -0.1700

Data Index: 1055155 (Open Web Text)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.0774. Min Act: -0.1700

Data Index: 920015 (Open Web Text)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.0865. Min Act: -0.1700

Data Index: 1297322 (Open Web Text)

Max Activating Token Index: 721

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.0721. Min Act: -0.1700

Data Index: 4572778 (Open Web Text)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.0816. Min Act: -0.1700

Data Index: 4182878 (Open Web Text)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.0841. Min Act: -0.1700

Data Index: 3591709 (Open Web Text)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.0816. Min Act: -0.1700

Data Index: 4683248 (Open Web Text)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1483. Min Range: -2.1483

Max Act: 2.0862. Min Act: -0.1700

Data Index: 4843928 (Open Web Text)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #19