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

Dataset: Open Web Text

Neuron 729 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: 3.4376. Min Range: -3.4376

Max Act: 3.4376. Min Act: -0.1700

Data Index: 6808926 (Open Web Text)

Max Activating Token Index: 81

Text #1

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4348. Min Act: -0.1700

Data Index: 4719442 (Open Web Text)

Max Activating Token Index: 496

Text #2

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.4150. Min Act: -0.1700

Data Index: 2522958 (Open Web Text)

Max Activating Token Index: 636

Text #3

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3968. Min Act: -0.1700

Data Index: 4659322 (Open Web Text)

Max Activating Token Index: 996

Text #4

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3818. Min Act: -0.1700

Data Index: 8484491 (Open Web Text)

Max Activating Token Index: 551

Text #5

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3523. Min Act: -0.1700

Data Index: 1859953 (Open Web Text)

Max Activating Token Index: 474

Text #6

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3327. Min Act: -0.1700

Data Index: 571624 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3428. Min Act: -0.1700

Data Index: 4316615 (Open Web Text)

Max Activating Token Index: 520

Text #8

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3325. Min Act: -0.1700

Data Index: 2852235 (Open Web Text)

Max Activating Token Index: 878

Text #9

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3130. Min Act: -0.1700

Data Index: 849656 (Open Web Text)

Max Activating Token Index: 497

Text #10

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3344. Min Act: -0.1700

Data Index: 5585821 (Open Web Text)

Max Activating Token Index: 313

Text #11

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3114. Min Act: -0.1700

Data Index: 5929912 (Open Web Text)

Max Activating Token Index: 147

Text #12

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3265. Min Act: -0.1700

Data Index: 4373091 (Open Web Text)

Max Activating Token Index: 524

Text #13

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.2935. Min Act: -0.1700

Data Index: 5702589 (Open Web Text)

Max Activating Token Index: 459

Text #14

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.2888. Min Act: -0.1700

Data Index: 5504927 (Open Web Text)

Max Activating Token Index: 320

Text #15

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.2930. Min Act: -0.1700

Data Index: 4823968 (Open Web Text)

Max Activating Token Index: 110

Text #16

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.2881. Min Act: -0.1700

Data Index: 5651991 (Open Web Text)

Max Activating Token Index: 545

Text #17

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.2655. Min Act: -0.1700

Data Index: 5162243 (Open Web Text)

Max Activating Token Index: 51

Text #18

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.2510. Min Act: -0.1700

Data Index: 4825719 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 3.4376. Min Range: -3.4376

Max Act: 3.3012. Min Act: -0.1700

Data Index: 3976211 (Open Web Text)

Max Activating Token Index: 371