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

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

Neuron 3867 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1126184 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4007. Min Act: -0.0000

Data Index: 291307 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3851. Min Act: -0.0000

Data Index: 997360 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1202978 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3544. Min Act: -0.0000

Data Index: 881914 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3302. Min Act: -0.0000

Data Index: 135677 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1048690 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3438. Min Act: -0.0000

Data Index: 357016 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3680. Min Act: -0.0000

Data Index: 427270 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1443502 (Python Code)

Max Activating Token Index: 284

Text #10

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3378. Min Act: -0.0000

Data Index: 118090 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3122. Min Act: -0.0000

Data Index: 563001 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1304198 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.2925. Min Act: -0.0000

Data Index: 427214 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.2779. Min Act: -0.0000

Data Index: 94771 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1022308 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.2814. Min Act: -0.0000

Data Index: 252629 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1266401 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.2926. Min Act: -0.0000

Data Index: 808509 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.2911. Min Act: -0.0000

Data Index: 969938 (C4 (Web Text))

Max Activating Token Index: 979