< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2654 in Layer 3

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: 2.9364. Min Range: -2.9364

Max Act: 2.9364. Min Act: -0.1700

Data Index: 7378551 (Open Web Text)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.8008. Min Act: -0.1700

Data Index: 1317162 (Open Web Text)

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.7775. Min Act: -0.1700

Data Index: 6316808 (Open Web Text)

Max Activating Token Index: 194

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.7729. Min Act: -0.1700

Data Index: 3201738 (Open Web Text)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.7719. Min Act: -0.1700

Data Index: 6853657 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.7752. Min Act: -0.1700

Data Index: 127126 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.7524. Min Act: -0.1700

Data Index: 3652015 (Open Web Text)

Max Activating Token Index: 721

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.7219. Min Act: -0.1700

Data Index: 2225601 (Open Web Text)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.7076. Min Act: -0.1700

Data Index: 1552286 (Open Web Text)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.6927. Min Act: -0.1700

Data Index: 55584 (Open Web Text)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.6459. Min Act: -0.1700

Data Index: 2280108 (Open Web Text)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.6879. Min Act: -0.1700

Data Index: 4663057 (Open Web Text)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.7171. Min Act: -0.1700

Data Index: 2427666 (Open Web Text)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.6707. Min Act: -0.1700

Data Index: 8770791 (Open Web Text)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.6696. Min Act: -0.1700

Data Index: 3469341 (Open Web Text)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.6675. Min Act: -0.1700

Data Index: 4834022 (Open Web Text)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.6685. Min Act: -0.1700

Data Index: 6017009 (Open Web Text)

Max Activating Token Index: 870

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.6648. Min Act: -0.1700

Data Index: 7599129 (Open Web Text)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.6674. Min Act: -0.1700

Data Index: 4353033 (Open Web Text)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9364. Min Range: -2.9364

Max Act: 2.6726. Min Act: -0.1700

Data Index: 2983722 (Open Web Text)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #19