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

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

Neuron 5266 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0207. Min Act: -0.0000

Data Index: 856826 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0198. Min Act: -0.0000

Data Index: 55183 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0221. Min Act: -0.0000

Data Index: 189786 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0194. Min Act: -0.0000

Data Index: 939781 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0186. Min Act: -0.0000

Data Index: 832840 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0193. Min Act: -0.0000

Data Index: 1237696 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0187. Min Act: -0.0000

Data Index: 277528 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0154. Min Act: -0.0000

Data Index: 1293946 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0173. Min Act: -0.0000

Data Index: 922307 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0162. Min Act: -0.0000

Data Index: 243727 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0167. Min Act: -0.0000

Data Index: 753919 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0176. Min Act: -0.0000

Data Index: 722573 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0162. Min Act: -0.0000

Data Index: 658407 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0152. Min Act: -0.0000

Data Index: 589978 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0154. Min Act: -0.0000

Data Index: 301974 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0154. Min Act: -0.0001

Data Index: 684014 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0122. Min Act: -0.0000

Data Index: 189172 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0150. Min Act: -0.0000

Data Index: 244114 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0150. Min Act: -0.0000

Data Index: 1519760 (Python Code)

Max Activating Token Index: 955

Text #19

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0150. Min Act: -0.0000

Data Index: 1484756 (Python Code)

Max Activating Token Index: 68