< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 691 in Layer 2

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: 2.0700. Min Range: -2.0700

Max Act: 2.0700. Min Act: -0.1694

Data Index: 3186298 (Open Web Text)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.0700. Min Range: -2.0700

Max Act: 2.0256. Min Act: -0.1700

Data Index: 1658288 (Open Web Text)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.9853. Min Act: -0.1699

Data Index: 2804976 (Open Web Text)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.9519. Min Act: -0.1700

Data Index: 6249803 (Open Web Text)

Max Activating Token Index: 451

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.9326. Min Act: -0.1700

Data Index: 757720 (Open Web Text)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.9263. Min Act: -0.1700

Data Index: 1471459 (Open Web Text)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.9193. Min Act: -0.1700

Data Index: 4979883 (Open Web Text)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.9245. Min Act: -0.1700

Data Index: 2366700 (Open Web Text)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.9066. Min Act: -0.1700

Data Index: 1987311 (Open Web Text)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.9022. Min Act: -0.1700

Data Index: 7574354 (Open Web Text)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.9042. Min Act: -0.1700

Data Index: 915656 (Open Web Text)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.8904. Min Act: -0.1700

Data Index: 5183872 (Open Web Text)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.8983. Min Act: -0.1700

Data Index: 4401550 (Open Web Text)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.8798. Min Act: -0.1700

Data Index: 453918 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.8791. Min Act: -0.1700

Data Index: 1901289 (Open Web Text)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.8955. Min Act: -0.1700

Data Index: 1893001 (Open Web Text)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.8811. Min Act: -0.1698

Data Index: 5012198 (Open Web Text)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.8887. Min Act: -0.1700

Data Index: 2450319 (Open Web Text)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.8825. Min Act: -0.1700

Data Index: 2201152 (Open Web Text)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.0700. Min Range: -2.0700

Max Act: 1.8844. Min Act: -0.1700

Data Index: 6311746 (Open Web Text)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #19