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

Dataset: Open Web Text

Neuron 440 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: 3.1482. Min Range: -3.1482

Max Act: 3.1482. Min Act: -0.1700

Data Index: 6890111 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.1058. Min Act: -0.1700

Data Index: 8394619 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.1144. Min Act: -0.1700

Data Index: 5664895 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0637. Min Act: -0.1700

Data Index: 1896707 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0651. Min Act: -0.1700

Data Index: 1636425 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0707. Min Act: -0.1700

Data Index: 3231486 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0488. Min Act: -0.1700

Data Index: 6007882 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0493. Min Act: -0.1700

Data Index: 4564 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0478. Min Act: -0.1700

Data Index: 7784675 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0358. Min Act: -0.1700

Data Index: 8735826 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0403. Min Act: -0.1700

Data Index: 2880824 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0294. Min Act: -0.1700

Data Index: 1437945 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0390. Min Act: -0.1700

Data Index: 6752328 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0073. Min Act: -0.1700

Data Index: 1751568 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0192. Min Act: -0.1700

Data Index: 3787395 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0171. Min Act: -0.1700

Data Index: 1180097 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0256. Min Act: -0.1700

Data Index: 8262420 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0227. Min Act: -0.1700

Data Index: 385553 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0196. Min Act: -0.1700

Data Index: 1431609 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0209. Min Act: -0.1700

Data Index: 983824 (Open Web Text)

Max Activating Token Index: 3