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

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

Neuron 4752 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0224. Min Act: -0.0002

Data Index: 120215 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0220. Min Act: -0.0002

Data Index: 223427 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0218. Min Act: -0.0002

Data Index: 64729 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0217. Min Act: -0.0002

Data Index: 211506 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0215. Min Act: -0.0002

Data Index: 35449 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1383684 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0211. Min Act: -0.0002

Data Index: 85845 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0210. Min Act: -0.0002

Data Index: 141309 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1255868 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0214. Min Act: -0.0002

Data Index: 300749 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1567335 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0211. Min Act: -0.0002

Data Index: 293575 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1168463 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0210. Min Act: -0.0002

Data Index: 739499 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0210. Min Act: -0.0002

Data Index: 713987 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1375289 (Python Code)

Max Activating Token Index: 80

Text #16

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0209. Min Act: -0.0002

Data Index: 716726 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0209. Min Act: -0.0002

Data Index: 790983 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1254329 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0207. Min Act: -0.0002

Data Index: 80899 (C4 (Web Text))

Max Activating Token Index: 5