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

Dataset: Open Web Text

Neuron 368 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: 3.3444. Min Range: -3.3444

Max Act: 3.3444. Min Act: -0.1700

Data Index: 6139326 (Open Web Text)

Max Activating Token Index: 933

Text #1

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.3088. Min Act: -0.1700

Data Index: 7034460 (Open Web Text)

Max Activating Token Index: 862

Text #2

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.3239. Min Act: -0.1700

Data Index: 6937170 (Open Web Text)

Max Activating Token Index: 669

Text #3

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.3118. Min Act: -0.1700

Data Index: 6574017 (Open Web Text)

Max Activating Token Index: 363

Text #4

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.1818. Min Act: -0.1700

Data Index: 4392124 (Open Web Text)

Max Activating Token Index: 742

Text #5

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2378. Min Act: -0.1700

Data Index: 3565947 (Open Web Text)

Max Activating Token Index: 365

Text #6

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2132. Min Act: -0.1700

Data Index: 8028613 (Open Web Text)

Max Activating Token Index: 653

Text #7

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2487. Min Act: -0.1700

Data Index: 2621510 (Open Web Text)

Max Activating Token Index: 626

Text #8

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2527. Min Act: -0.1700

Data Index: 7142041 (Open Web Text)

Max Activating Token Index: 383

Text #9

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2364. Min Act: -0.1700

Data Index: 7510079 (Open Web Text)

Max Activating Token Index: 358

Text #10

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2339. Min Act: -0.1700

Data Index: 1046694 (Open Web Text)

Max Activating Token Index: 562

Text #11

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2324. Min Act: -0.1700

Data Index: 938119 (Open Web Text)

Max Activating Token Index: 592

Text #12

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2052. Min Act: -0.1700

Data Index: 5295867 (Open Web Text)

Max Activating Token Index: 581

Text #13

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.1966. Min Act: -0.1700

Data Index: 1740851 (Open Web Text)

Max Activating Token Index: 894

Text #14

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2295. Min Act: -0.1700

Data Index: 7708202 (Open Web Text)

Max Activating Token Index: 593

Text #15

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.1689. Min Act: -0.1700

Data Index: 8011716 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2335. Min Act: -0.1700

Data Index: 6199884 (Open Web Text)

Max Activating Token Index: 666

Text #17

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.1972. Min Act: -0.1700

Data Index: 4983182 (Open Web Text)

Max Activating Token Index: 248

Text #18

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2135. Min Act: -0.1700

Data Index: 7395111 (Open Web Text)

Max Activating Token Index: 607

Text #19

Max Range: 3.3444. Min Range: -3.3444

Max Act: 3.2272. Min Act: -0.1700

Data Index: 3527738 (Open Web Text)

Max Activating Token Index: 982