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

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

Neuron 3755 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0918. Min Range: -3.0918

Max Act: 3.0918. Min Act: -0.0001

Data Index: 923894 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.9229. Min Act: -0.0001

Data Index: 1611282 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.4621. Min Act: -0.0001

Data Index: 1394998 (Python Code)

Max Activating Token Index: 686

Text #3

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.6306. Min Act: -0.0001

Data Index: 831858 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.2693. Min Act: -0.0001

Data Index: 1529223 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.3494. Min Act: -0.0001

Data Index: 1604585 (Python Code)

Max Activating Token Index: 733

Text #6

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.3526. Min Act: -0.0001

Data Index: 1623491 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.4562. Min Act: -0.0001

Data Index: 956248 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.3274. Min Act: -0.0001

Data Index: 1587599 (Python Code)

Max Activating Token Index: 284

Text #9

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.3159. Min Act: -0.0001

Data Index: 1064162 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.1431. Min Act: -0.0001

Data Index: 706810 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.1758. Min Act: -0.0001

Data Index: 1172853 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.2317. Min Act: -0.0001

Data Index: 1521576 (Python Code)

Max Activating Token Index: 905

Text #13

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.2551. Min Act: -0.0001

Data Index: 143071 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.0380. Min Act: -0.0001

Data Index: 1590463 (Python Code)

Max Activating Token Index: 221

Text #15

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.0156. Min Act: -0.0001

Data Index: 1149373 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.0662. Min Act: -0.0001

Data Index: 997596 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.0507. Min Act: -0.0001

Data Index: 404668 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 3.0918. Min Range: -3.0918

Max Act: 1.1198. Min Act: -0.0001

Data Index: 31526 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 3.0918. Min Range: -3.0918

Max Act: 0.9951. Min Act: -0.0001

Data Index: 661342 (C4 (Web Text))

Max Activating Token Index: 412