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

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

Neuron 5359 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1358486 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4772. Min Act: -0.0000

Data Index: 604708 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1358605 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4495. Min Act: -0.0000

Data Index: 780947 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1023100 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4045. Min Act: -0.0000

Data Index: 436262 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4371. Min Act: -0.0000

Data Index: 294165 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4236. Min Act: -0.0000

Data Index: 480964 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4196. Min Act: -0.0000

Data Index: 140881 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4194. Min Act: -0.0000

Data Index: 350763 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4314. Min Act: -0.0000

Data Index: 139434 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4052. Min Act: -0.0000

Data Index: 867204 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3731. Min Act: -0.0000

Data Index: 716545 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1103070 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1134695 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1249568 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3870. Min Act: -0.0000

Data Index: 640701 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1124456 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3860. Min Act: -0.0000

Data Index: 277491 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3592. Min Act: -0.0000

Data Index: 970868 (C4 (Web Text))

Max Activating Token Index: 974