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

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

Neuron 2601 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1155846 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7417. Min Act: -0.0000

Data Index: 150076 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7392. Min Act: -0.0000

Data Index: 131962 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7152. Min Act: -0.0000

Data Index: 745881 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7511. Min Act: -0.0000

Data Index: 788868 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7464. Min Act: -0.0000

Data Index: 287979 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6889. Min Act: -0.0000

Data Index: 964772 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6835. Min Act: -0.0000

Data Index: 270915 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1074435 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6474. Min Act: -0.0000

Data Index: 102758 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6892. Min Act: -0.0000

Data Index: 180659 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7047. Min Act: -0.0000

Data Index: 984448 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6404. Min Act: -0.0000

Data Index: 421221 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6369. Min Act: -0.0000

Data Index: 309914 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6619. Min Act: -0.0000

Data Index: 1290831 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6111. Min Act: -0.0000

Data Index: 179453 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1319692 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6223. Min Act: -0.0000

Data Index: 938297 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6354. Min Act: -0.0000

Data Index: 78533 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.5937. Min Act: -0.0000

Data Index: 999207 (C4 (Web Text))

Max Activating Token Index: 243