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

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

Neuron 195 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: 5.6176. Min Range: -5.6176

Max Act: 5.6176. Min Act: -0.1700

Data Index: 167933 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.9301. Min Act: -0.1700

Data Index: 857259 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.0239. Min Act: -0.1700

Data Index: 1292432 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.9301. Min Act: -0.1700

Data Index: 109856 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.9301. Min Act: -0.1700

Data Index: 182659 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.9301. Min Act: -0.1700

Data Index: 1165032 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.8988. Min Act: -0.1700

Data Index: 1180424 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.8363. Min Act: -0.1700

Data Index: 886868 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.8676. Min Act: -0.1700

Data Index: 32336 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.8363. Min Act: -0.1700

Data Index: 1064368 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.7738. Min Act: -0.1700

Data Index: 392087 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.8363. Min Act: -0.1700

Data Index: 1327447 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.8676. Min Act: -0.1699

Data Index: 1016920 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.7738. Min Act: -0.1700

Data Index: 1097241 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.8051. Min Act: -0.1700

Data Index: 848042 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.7738. Min Act: -0.1700

Data Index: 531323 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.7113. Min Act: -0.1700

Data Index: 1318024 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.7113. Min Act: -0.1700

Data Index: 522528 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.7426. Min Act: -0.1700

Data Index: 1183623 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 5.6176. Min Range: -5.6176

Max Act: 4.7426. Min Act: -0.1700

Data Index: 653021 (C4 (Web Text))

Max Activating Token Index: 354