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

Dataset: Open Web Text

Neuron 401 in Layer 1

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: 1.3162. Min Range: -1.3162

Max Act: 1.3162. Min Act: -0.1700

Data Index: 6545118 (Open Web Text)

Max Activating Token Index: 175

Text #1

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2681. Min Act: -0.1700

Data Index: 7748385 (Open Web Text)

Max Activating Token Index: 370

Text #2

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2549. Min Act: -0.1700

Data Index: 4828887 (Open Web Text)

Max Activating Token Index: 686

Text #3

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2451. Min Act: -0.1700

Data Index: 5400127 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2494. Min Act: -0.1700

Data Index: 48291 (Open Web Text)

Max Activating Token Index: 465

Text #5

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2457. Min Act: -0.1697

Data Index: 8226261 (Open Web Text)

Max Activating Token Index: 459

Text #6

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2485. Min Act: -0.1700

Data Index: 484564 (Open Web Text)

Max Activating Token Index: 571

Text #7

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2495. Min Act: -0.1700

Data Index: 4523775 (Open Web Text)

Max Activating Token Index: 158

Text #8

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2519. Min Act: -0.1699

Data Index: 3376335 (Open Web Text)

Max Activating Token Index: 982

Text #9

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2321. Min Act: -0.1699

Data Index: 255703 (Open Web Text)

Max Activating Token Index: 141

Text #10

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2480. Min Act: -0.1700

Data Index: 7981422 (Open Web Text)

Max Activating Token Index: 925

Text #11

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2367. Min Act: -0.1700

Data Index: 5790117 (Open Web Text)

Max Activating Token Index: 69

Text #12

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2273. Min Act: -0.1700

Data Index: 2767853 (Open Web Text)

Max Activating Token Index: 836

Text #13

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2302. Min Act: -0.1700

Data Index: 3463428 (Open Web Text)

Max Activating Token Index: 1017

Text #14

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2291. Min Act: -0.1700

Data Index: 623766 (Open Web Text)

Max Activating Token Index: 534

Text #15

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2192. Min Act: -0.1699

Data Index: 7924475 (Open Web Text)

Max Activating Token Index: 724

Text #16

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2380. Min Act: -0.1700

Data Index: 4589176 (Open Web Text)

Max Activating Token Index: 885

Text #17

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2281. Min Act: -0.1696

Data Index: 4111031 (Open Web Text)

Max Activating Token Index: 280

Text #18

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2265. Min Act: -0.1700

Data Index: 7687503 (Open Web Text)

Max Activating Token Index: 658

Text #19

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2212. Min Act: -0.1699

Data Index: 2250508 (Open Web Text)

Max Activating Token Index: 337