< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1278 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.7683. Min Act: -0.1700

Data Index: 6958620 (Open Web Text)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.7129. Min Act: -0.1700

Data Index: 1434850 (Open Web Text)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.7512. Min Act: -0.1700

Data Index: 305349 (Open Web Text)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.6749. Min Act: -0.1700

Data Index: 140523 (Open Web Text)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.6867. Min Act: -0.1700

Data Index: 351136 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.6947. Min Act: -0.1700

Data Index: 4902270 (Open Web Text)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.6411. Min Act: -0.1700

Data Index: 3681793 (Open Web Text)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.6423. Min Act: -0.1700

Data Index: 761972 (Open Web Text)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.6164. Min Act: -0.1700

Data Index: 7198935 (Open Web Text)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.4983. Min Act: -0.1700

Data Index: 4979731 (Open Web Text)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.4969. Min Act: -0.1700

Data Index: 7626879 (Open Web Text)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.5028. Min Act: -0.1700

Data Index: 5286955 (Open Web Text)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.4996. Min Act: -0.1700

Data Index: 1969823 (Open Web Text)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.4533. Min Act: -0.1700

Data Index: 5025874 (Open Web Text)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.4611. Min Act: -0.1700

Data Index: 5873844 (Open Web Text)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.4504. Min Act: -0.1700

Data Index: 6394341 (Open Web Text)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.4673. Min Act: -0.1700

Data Index: 4109635 (Open Web Text)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.4751. Min Act: -0.1700

Data Index: 272275 (Open Web Text)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.4503. Min Act: -0.1700

Data Index: 7075888 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.7683. Min Range: -4.7683

Max Act: 4.4665. Min Act: -0.1700

Data Index: 1473903 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #19