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

Dataset: Open Web Text

Neuron 2444 in Layer 4

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: 3.4329. Min Range: -3.4329

Max Act: 3.4329. Min Act: -0.1700

Data Index: 3153242 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.4219. Min Act: -0.1700

Data Index: 8597839 (Open Web Text)

Max Activating Token Index: 641

Text #2

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.3779. Min Act: -0.1700

Data Index: 1264142 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.3908. Min Act: -0.1700

Data Index: 2502015 (Open Web Text)

Max Activating Token Index: 201

Text #4

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.3617. Min Act: -0.1700

Data Index: 6536708 (Open Web Text)

Max Activating Token Index: 419

Text #5

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.3361. Min Act: -0.1700

Data Index: 8461620 (Open Web Text)

Max Activating Token Index: 946

Text #6

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.3067. Min Act: -0.1700

Data Index: 6337934 (Open Web Text)

Max Activating Token Index: 936

Text #7

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2535. Min Act: -0.1700

Data Index: 2890593 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2758. Min Act: -0.1700

Data Index: 8592382 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2820. Min Act: -0.1700

Data Index: 5515184 (Open Web Text)

Max Activating Token Index: 928

Text #10

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2518. Min Act: -0.1700

Data Index: 5386668 (Open Web Text)

Max Activating Token Index: 930

Text #11

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2319. Min Act: -0.1700

Data Index: 2243655 (Open Web Text)

Max Activating Token Index: 540

Text #12

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2161. Min Act: -0.1700

Data Index: 3722594 (Open Web Text)

Max Activating Token Index: 518

Text #13

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2546. Min Act: -0.1700

Data Index: 7172066 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2357. Min Act: -0.1700

Data Index: 8521100 (Open Web Text)

Max Activating Token Index: 484

Text #15

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2322. Min Act: -0.1700

Data Index: 6740135 (Open Web Text)

Max Activating Token Index: 775

Text #16

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2443. Min Act: -0.1700

Data Index: 6338103 (Open Web Text)

Max Activating Token Index: 174

Text #17

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2438. Min Act: -0.1700

Data Index: 619749 (Open Web Text)

Max Activating Token Index: 952

Text #18

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2117. Min Act: -0.1700

Data Index: 4336732 (Open Web Text)

Max Activating Token Index: 608

Text #19

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.2182. Min Act: -0.1700

Data Index: 4851048 (Open Web Text)

Max Activating Token Index: 94