Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 252 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.8367. Min Act: -0.0001

Data Index: 719271 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7845. Min Act: -0.0001

Data Index: 872867 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7182. Min Act: -0.0000

Data Index: 157275 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1277288 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7281. Min Act: -0.0001

Data Index: 515704 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7346. Min Act: -0.0000

Data Index: 515123 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.7096. Min Act: -0.0001

Data Index: 1270410 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6587. Min Act: -0.0001

Data Index: 922644 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5744. Min Act: -0.0001

Data Index: 98700 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5993. Min Act: -0.0001

Data Index: 788623 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6237. Min Act: -0.0000

Data Index: 780432 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5677. Min Act: -0.0001

Data Index: 461455 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.6227. Min Act: -0.0000

Data Index: 910729 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5726. Min Act: -0.0000

Data Index: 867651 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5482. Min Act: -0.0000

Data Index: 847761 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5842. Min Act: -0.0001

Data Index: 410642 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5627. Min Act: -0.0000

Data Index: 65187 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5998. Min Act: -0.0001

Data Index: 635989 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1029088 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.8367. Min Range: -0.8367

Max Act: 0.5453. Min Act: -0.0001

Data Index: 49555 (C4 (Web Text))

Max Activating Token Index: 494