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

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

Neuron 188 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0006

Data Index: 11456 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0393. Min Act: -0.0006

Data Index: 649408 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0398. Min Act: -0.0006

Data Index: 489458 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0371. Min Act: -0.0006

Data Index: 847045 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0373. Min Act: -0.0006

Data Index: 363964 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0370. Min Act: -0.0006

Data Index: 789982 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0367. Min Act: -0.0006

Data Index: 526218 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0367. Min Act: -0.0006

Data Index: 914819 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0359. Min Act: -0.0006

Data Index: 1035427 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0360. Min Act: -0.0006

Data Index: 642323 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0359. Min Act: -0.0007

Data Index: 845960 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0373. Min Act: -0.0006

Data Index: 930013 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0355. Min Act: -0.0006

Data Index: 650333 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0354. Min Act: -0.0006

Data Index: 1264535 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0359. Min Act: -0.0006

Data Index: 739407 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0338. Min Act: -0.0006

Data Index: 67704 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0360. Min Act: -0.0006

Data Index: 377770 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0351. Min Act: -0.0006

Data Index: 76808 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0359. Min Act: -0.0006

Data Index: 844020 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0341. Min Act: -0.0006

Data Index: 656737 (C4 (Web Text))

Max Activating Token Index: 853