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

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

Neuron 5336 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1229229 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1087663 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7050. Min Act: -0.0000

Data Index: 237504 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6895. Min Act: -0.0000

Data Index: 919718 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6742. Min Act: -0.0000

Data Index: 604849 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6973. Min Act: -0.0000

Data Index: 511766 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1298455 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6165. Min Act: -0.0000

Data Index: 351136 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1038904 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5537. Min Act: -0.0000

Data Index: 732991 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5934. Min Act: -0.0000

Data Index: 763453 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5396. Min Act: -0.0000

Data Index: 289856 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5657. Min Act: -0.0000

Data Index: 862367 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5450. Min Act: -0.0000

Data Index: 535613 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5858. Min Act: -0.0000

Data Index: 435026 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5574. Min Act: -0.0000

Data Index: 789152 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5632. Min Act: -0.0000

Data Index: 697239 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5397. Min Act: -0.0000

Data Index: 765268 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5462. Min Act: -0.0000

Data Index: 271669 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5177. Min Act: -0.0000

Data Index: 853607 (C4 (Web Text))

Max Activating Token Index: 66