Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2126 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1649936 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3397. Min Act: -0.0001

Data Index: 1298880 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3139. Min Act: -0.0001

Data Index: 707019 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3116. Min Act: -0.0000

Data Index: 710855 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3133. Min Act: -0.0001

Data Index: 961509 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1652249 (Python Code)

Max Activating Token Index: 942

Text #6

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3000. Min Act: -0.0000

Data Index: 730113 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1461094 (Python Code)

Max Activating Token Index: 313

Text #8

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2896. Min Act: -0.0000

Data Index: 734074 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2989. Min Act: -0.0000

Data Index: 729505 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2872. Min Act: -0.0001

Data Index: 1487542 (Python Code)

Max Activating Token Index: 191

Text #11

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1225697 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2708. Min Act: -0.0000

Data Index: 85796 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2871. Min Act: -0.0000

Data Index: 948676 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2797. Min Act: -0.0000

Data Index: 799280 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2760. Min Act: -0.0001

Data Index: 273250 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2768. Min Act: -0.0000

Data Index: 788550 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1302847 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2811. Min Act: -0.0001

Data Index: 661315 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2710. Min Act: -0.0000

Data Index: 283936 (C4 (Web Text))

Max Activating Token Index: 415