< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1664 in Layer 0

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: 2.9955. Min Range: -2.9955

Max Act: 2.9955. Min Act: -0.1700

Data Index: 2473012 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.9955. Min Act: -0.1700

Data Index: 7225217 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8997. Min Act: -0.1700

Data Index: 2012095 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8997. Min Act: -0.1700

Data Index: 7862855 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8997. Min Act: -0.1700

Data Index: 1866396 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8997. Min Act: -0.1700

Data Index: 238976 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8976. Min Act: -0.1700

Data Index: 2254203 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8997. Min Act: -0.1700

Data Index: 170504 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8709. Min Act: -0.1700

Data Index: 2045229 (Open Web Text)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8642. Min Act: -0.1700

Data Index: 7529446 (Open Web Text)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8647. Min Act: -0.1700

Data Index: 7877846 (Open Web Text)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8608. Min Act: -0.1700

Data Index: 2110255 (Open Web Text)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8434. Min Act: -0.1700

Data Index: 5549048 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8568. Min Act: -0.1700

Data Index: 7591809 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8540. Min Act: -0.1700

Data Index: 8410581 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8440. Min Act: -0.1700

Data Index: 837490 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8467. Min Act: -0.1700

Data Index: 2509732 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8287. Min Act: -0.1700

Data Index: 4245389 (Open Web Text)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8420. Min Act: -0.1700

Data Index: 4466283 (Open Web Text)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9955. Min Range: -2.9955

Max Act: 2.8318. Min Act: -0.1700

Data Index: 1197261 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #19