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

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

Neuron 787 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: 5.2738. Min Range: -5.2738

Max Act: 5.2738. Min Act: -0.1700

Data Index: 1239384 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.9301. Min Act: -0.1700

Data Index: 1303062 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.8832. Min Act: -0.1700

Data Index: 509038 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.8676. Min Act: -0.1700

Data Index: 928471 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.8832. Min Act: -0.1700

Data Index: 870954 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.8207. Min Act: -0.1700

Data Index: 754215 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.7738. Min Act: -0.1700

Data Index: 1052146 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.7426. Min Act: -0.1700

Data Index: 374895 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.7269. Min Act: -0.1700

Data Index: 198683 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.7582. Min Act: -0.1700

Data Index: 239299 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.6176. Min Act: -0.1700

Data Index: 1251950 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.6801. Min Act: -0.1700

Data Index: 1157316 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.6644. Min Act: -0.1700

Data Index: 1101411 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.6801. Min Act: -0.1700

Data Index: 76819 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.6332. Min Act: -0.1700

Data Index: 833997 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.6488. Min Act: -0.1700

Data Index: 582978 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.6332. Min Act: -0.1700

Data Index: 759125 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.6176. Min Act: -0.1700

Data Index: 371522 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.5707. Min Act: -0.1700

Data Index: 133041 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.5707. Min Act: -0.1700

Data Index: 428069 (C4 (Web Text))

Max Activating Token Index: 295