Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 746 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.6399. Min Act: -0.0000

Data Index: 400972 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.4060. Min Act: -0.0000

Data Index: 74541 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.2413. Min Act: -0.0000

Data Index: 142030 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 3.6399. Min Range: -3.6399

Max Act: 3.2366. Min Act: -0.0000

Data Index: 785549 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.9291. Min Act: -0.0000

Data Index: 930929 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.8616. Min Act: -0.0000

Data Index: 1061557 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.8383. Min Act: -0.0000

Data Index: 48963 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.6436. Min Act: -0.0000

Data Index: 1616211 (Python Code)

Max Activating Token Index: 980

Text #8

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.7446. Min Act: -0.0000

Data Index: 31913 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.4589. Min Act: -0.0000

Data Index: 39782 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.2883. Min Act: -0.0000

Data Index: 1109528 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.3818. Min Act: -0.0000

Data Index: 245438 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.3757. Min Act: -0.0000

Data Index: 628111 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.3336. Min Act: -0.0000

Data Index: 707270 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.3180. Min Act: -0.0000

Data Index: 78007 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.3061. Min Act: -0.0000

Data Index: 1158288 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.3025. Min Act: -0.0000

Data Index: 677522 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.1296. Min Act: -0.0000

Data Index: 1431248 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.1194. Min Act: -0.0000

Data Index: 61740 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 3.6399. Min Range: -3.6399

Max Act: 2.3001. Min Act: -0.0000

Data Index: 627880 (C4 (Web Text))

Max Activating Token Index: 841