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

Dataset: Open Web Text

Neuron 2173 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: 4.1477. Min Range: -4.1477

Max Act: 4.1477. Min Act: -0.1700

Data Index: 6919357 (Open Web Text)

Max Activating Token Index: 989

Text #1

Max Range: 4.1477. Min Range: -4.1477

Max Act: 4.0446. Min Act: -0.1700

Data Index: 1828232 (Open Web Text)

Max Activating Token Index: 359

Text #2

Max Range: 4.1477. Min Range: -4.1477

Max Act: 4.0726. Min Act: -0.1696

Data Index: 6891027 (Open Web Text)

Max Activating Token Index: 925

Text #3

Max Range: 4.1477. Min Range: -4.1477

Max Act: 4.0216. Min Act: -0.1700

Data Index: 8353796 (Open Web Text)

Max Activating Token Index: 701

Text #4

Max Range: 4.1477. Min Range: -4.1477

Max Act: 4.0075. Min Act: -0.1700

Data Index: 7129235 (Open Web Text)

Max Activating Token Index: 431

Text #5

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9847. Min Act: -0.1700

Data Index: 4792761 (Open Web Text)

Max Activating Token Index: 490

Text #6

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9895. Min Act: -0.1700

Data Index: 3526519 (Open Web Text)

Max Activating Token Index: 292

Text #7

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9933. Min Act: -0.1700

Data Index: 162865 (Open Web Text)

Max Activating Token Index: 328

Text #8

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9963. Min Act: -0.1700

Data Index: 4213929 (Open Web Text)

Max Activating Token Index: 720

Text #9

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9641. Min Act: -0.1699

Data Index: 1044863 (Open Web Text)

Max Activating Token Index: 524

Text #10

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9705. Min Act: -0.1700

Data Index: 6773344 (Open Web Text)

Max Activating Token Index: 420

Text #11

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9689. Min Act: -0.1700

Data Index: 6773341 (Open Web Text)

Max Activating Token Index: 878

Text #12

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9509. Min Act: -0.1700

Data Index: 8208478 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9483. Min Act: -0.1700

Data Index: 6238422 (Open Web Text)

Max Activating Token Index: 857

Text #14

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9480. Min Act: -0.1700

Data Index: 2682892 (Open Web Text)

Max Activating Token Index: 253

Text #15

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9341. Min Act: -0.1699

Data Index: 4523958 (Open Web Text)

Max Activating Token Index: 477

Text #16

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9445. Min Act: -0.1699

Data Index: 3001774 (Open Web Text)

Max Activating Token Index: 876

Text #17

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9097. Min Act: -0.1700

Data Index: 4139420 (Open Web Text)

Max Activating Token Index: 862

Text #18

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9307. Min Act: -0.1700

Data Index: 6634197 (Open Web Text)

Max Activating Token Index: 339

Text #19

Max Range: 4.1477. Min Range: -4.1477

Max Act: 3.9351. Min Act: -0.1700

Data Index: 6497834 (Open Web Text)

Max Activating Token Index: 129