Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 453 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0277. Min Act: -0.0006

Data Index: 329154 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0269. Min Act: -0.0006

Data Index: 821495 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0264. Min Act: -0.0006

Data Index: 16972 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0240. Min Act: -0.0006

Data Index: 624725 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0249. Min Act: -0.0006

Data Index: 99643 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0241. Min Act: -0.0006

Data Index: 196258 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1121463 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0227. Min Act: -0.0006

Data Index: 40309 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1069727 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1163486 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0225. Min Act: -0.0006

Data Index: 515813 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0223. Min Act: -0.0006

Data Index: 340643 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0222. Min Act: -0.0006

Data Index: 491987 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1146174 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0216. Min Act: -0.0006

Data Index: 276501 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0214. Min Act: -0.0006

Data Index: 170536 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1137995 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1104070 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1176582 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0205. Min Act: -0.0006

Data Index: 613842 (C4 (Web Text))

Max Activating Token Index: 6