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

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

Neuron 2022 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0002

Data Index: 151442 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0553. Min Act: -0.0002

Data Index: 722663 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0407. Min Act: -0.0002

Data Index: 604034 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1231068 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1292158 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0388. Min Act: -0.0002

Data Index: 230719 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0427. Min Act: -0.0002

Data Index: 611972 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1503527 (Python Code)

Max Activating Token Index: 113

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0325. Min Act: -0.0002

Data Index: 807695 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0394. Min Act: -0.0002

Data Index: 899072 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1148350 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0404. Min Act: -0.0002

Data Index: 504564 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0391. Min Act: -0.0002

Data Index: 712721 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0315. Min Act: -0.0002

Data Index: 524214 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1215739 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0382. Min Act: -0.0002

Data Index: 603740 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0354. Min Act: -0.0002

Data Index: 842470 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0381. Min Act: -0.0002

Data Index: 553260 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1340402 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0340. Min Act: -0.0002

Data Index: 767819 (C4 (Web Text))

Max Activating Token Index: 286