Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1018 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.8503. Min Range: -8.8503

Max Act: 8.8503. Min Act: -0.1700

Data Index: 715681 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 8.8503. Min Range: -8.8503

Max Act: 8.0066. Min Act: -0.1700

Data Index: 918323 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.8191. Min Act: -0.1700

Data Index: 731742 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.8191. Min Act: -0.1700

Data Index: 344801 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.7566. Min Act: -0.1700

Data Index: 391570 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.6941. Min Act: -0.1700

Data Index: 1171328 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.6628. Min Act: -0.1700

Data Index: 494233 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.6316. Min Act: -0.1700

Data Index: 226337 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.5378. Min Act: -0.1700

Data Index: 845773 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.5378. Min Act: -0.1700

Data Index: 645097 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.5378. Min Act: -0.1700

Data Index: 456516 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.4441. Min Act: -0.1700

Data Index: 574108 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.4128. Min Act: -0.1700

Data Index: 42377 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.4753. Min Act: -0.1700

Data Index: 1331449 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.3816. Min Act: -0.1700

Data Index: 158948 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.3503. Min Act: -0.1700

Data Index: 262671 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.3503. Min Act: -0.1700

Data Index: 187070 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.3503. Min Act: -0.1699

Data Index: 1041498 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.3816. Min Act: -0.1700

Data Index: 615934 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 8.8503. Min Range: -8.8503

Max Act: 7.2878. Min Act: -0.1700

Data Index: 1004160 (C4 (Web Text))

Max Activating Token Index: 540