Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2155 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.8204. Min Act: -0.0000

Data Index: 155789 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.8026. Min Act: -0.0000

Data Index: 949314 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1171177 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.6843. Min Act: -0.0000

Data Index: 208830 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.6441. Min Act: -0.0000

Data Index: 93001 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1251883 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.6846. Min Act: -0.0000

Data Index: 381470 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.6176. Min Act: -0.0000

Data Index: 802721 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.5838. Min Act: -0.0000

Data Index: 353625 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.6586. Min Act: -0.0000

Data Index: 956563 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.6022. Min Act: -0.0000

Data Index: 914163 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.5854. Min Act: -0.0000

Data Index: 369026 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.5564. Min Act: -0.0000

Data Index: 18110 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1079075 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1198764 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.6006. Min Act: -0.0000

Data Index: 721591 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.5733. Min Act: -0.0000

Data Index: 440294 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.5429. Min Act: -0.0000

Data Index: 248614 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.5648. Min Act: -0.0000

Data Index: 794455 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.8204. Min Range: -0.8204

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1047986 (C4 (Web Text))

Max Activating Token Index: 300