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

Dataset: Open Web Text

Neuron 810 in Layer 5

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: 3.4616. Min Range: -3.4616

Max Act: 3.4616. Min Act: -0.1700

Data Index: 2581843 (Open Web Text)

Max Activating Token Index: 977

Text #1

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3932. Min Act: -0.1700

Data Index: 8209069 (Open Web Text)

Max Activating Token Index: 853

Text #2

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3970. Min Act: -0.1700

Data Index: 1874722 (Open Web Text)

Max Activating Token Index: 344

Text #3

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3812. Min Act: -0.1700

Data Index: 2307689 (Open Web Text)

Max Activating Token Index: 589

Text #4

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3818. Min Act: -0.1700

Data Index: 3826674 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3783. Min Act: -0.1700

Data Index: 3350353 (Open Web Text)

Max Activating Token Index: 626

Text #6

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3809. Min Act: -0.1700

Data Index: 3491903 (Open Web Text)

Max Activating Token Index: 505

Text #7

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3818. Min Act: -0.1700

Data Index: 421840 (Open Web Text)

Max Activating Token Index: 212

Text #8

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3667. Min Act: -0.1700

Data Index: 5381206 (Open Web Text)

Max Activating Token Index: 264

Text #9

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3574. Min Act: -0.1700

Data Index: 3263850 (Open Web Text)

Max Activating Token Index: 928

Text #10

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3528. Min Act: -0.1700

Data Index: 5255947 (Open Web Text)

Max Activating Token Index: 301

Text #11

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3530. Min Act: -0.1700

Data Index: 1120371 (Open Web Text)

Max Activating Token Index: 808

Text #12

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3443. Min Act: -0.1700

Data Index: 3483360 (Open Web Text)

Max Activating Token Index: 481

Text #13

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3447. Min Act: -0.1700

Data Index: 4902100 (Open Web Text)

Max Activating Token Index: 601

Text #14

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3491. Min Act: -0.1700

Data Index: 7826711 (Open Web Text)

Max Activating Token Index: 546

Text #15

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3512. Min Act: -0.1700

Data Index: 6765517 (Open Web Text)

Max Activating Token Index: 488

Text #16

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3488. Min Act: -0.1700

Data Index: 1546808 (Open Web Text)

Max Activating Token Index: 736

Text #17

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3568. Min Act: -0.1700

Data Index: 4961146 (Open Web Text)

Max Activating Token Index: 507

Text #18

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3388. Min Act: -0.1700

Data Index: 4492099 (Open Web Text)

Max Activating Token Index: 920

Text #19

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.3211. Min Act: -0.1700

Data Index: 2698161 (Open Web Text)

Max Activating Token Index: 494