Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 107 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0226. Min Act: -0.0005

Data Index: 875617 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0220. Min Act: -0.0005

Data Index: 1008754 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0209. Min Act: -0.0006

Data Index: 198021 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1125419 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0211. Min Act: -0.0006

Data Index: 660563 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0212. Min Act: -0.0006

Data Index: 534746 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0211. Min Act: -0.0006

Data Index: 82906 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0206. Min Act: -0.0005

Data Index: 775148 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1056964 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0202. Min Act: -0.0006

Data Index: 276919 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0206. Min Act: -0.0005

Data Index: 206595 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0205. Min Act: -0.0006

Data Index: 995414 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1080954 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0198. Min Act: -0.0005

Data Index: 968629 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0198. Min Act: -0.0006

Data Index: 638128 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0202. Min Act: -0.0006

Data Index: 337685 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0197. Min Act: -0.0006

Data Index: 940509 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1262068 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0194. Min Act: -0.0006

Data Index: 880628 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0198. Min Act: -0.0006

Data Index: 248047 (C4 (Web Text))

Max Activating Token Index: 91