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

Dataset: Open Web Text

Neuron 1972 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: 1.5325. Min Range: -1.5325

Max Act: 1.5325. Min Act: -0.1700

Data Index: 3747469 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.5157. Min Act: -0.1697

Data Index: 2758325 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.4811. Min Act: -0.1700

Data Index: 4606803 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.4174. Min Act: -0.1699

Data Index: 236267 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3858. Min Act: -0.1700

Data Index: 388677 (Open Web Text)

Max Activating Token Index: 279

Text #5

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3777. Min Act: -0.1700

Data Index: 5437790 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3650. Min Act: -0.1700

Data Index: 6951946 (Open Web Text)

Max Activating Token Index: 1010

Text #7

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3481. Min Act: -0.1700

Data Index: 5495110 (Open Web Text)

Max Activating Token Index: 169

Text #8

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3595. Min Act: -0.1700

Data Index: 3667947 (Open Web Text)

Max Activating Token Index: 420

Text #9

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3338. Min Act: -0.1700

Data Index: 6043818 (Open Web Text)

Max Activating Token Index: 463

Text #10

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3366. Min Act: -0.1694

Data Index: 1645683 (Open Web Text)

Max Activating Token Index: 339

Text #11

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3402. Min Act: -0.1700

Data Index: 1334976 (Open Web Text)

Max Activating Token Index: 704

Text #12

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3319. Min Act: -0.1700

Data Index: 112216 (Open Web Text)

Max Activating Token Index: 795

Text #13

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3509. Min Act: -0.1700

Data Index: 5917829 (Open Web Text)

Max Activating Token Index: 159

Text #14

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3222. Min Act: -0.1699

Data Index: 5439140 (Open Web Text)

Max Activating Token Index: 845

Text #15

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3470. Min Act: -0.1700

Data Index: 4596434 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3077. Min Act: -0.1697

Data Index: 3104568 (Open Web Text)

Max Activating Token Index: 814

Text #17

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3397. Min Act: -0.1700

Data Index: 5928465 (Open Web Text)

Max Activating Token Index: 714

Text #18

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3291. Min Act: -0.1699

Data Index: 5510668 (Open Web Text)

Max Activating Token Index: 441

Text #19

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3320. Min Act: -0.1700

Data Index: 2236382 (Open Web Text)

Max Activating Token Index: 124