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

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

Neuron 9 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0233. Min Act: -0.0005

Data Index: 1537017 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0225. Min Act: -0.0005

Data Index: 1427410 (Python Code)

Max Activating Token Index: 612

Text #2

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1595739 (Python Code)

Max Activating Token Index: 881

Text #3

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0198. Min Act: -0.0005

Data Index: 151311 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0199. Min Act: -0.0005

Data Index: 1360636 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0193. Min Act: -0.0005

Data Index: 1576499 (Python Code)

Max Activating Token Index: 168

Text #6

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0184. Min Act: -0.0005

Data Index: 760078 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0197. Min Act: -0.0005

Data Index: 1505843 (Python Code)

Max Activating Token Index: 48

Text #8

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0192. Min Act: -0.0005

Data Index: 1372711 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0196. Min Act: -0.0005

Data Index: 1460269 (Python Code)

Max Activating Token Index: 230

Text #10

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0185. Min Act: -0.0005

Data Index: 1447284 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0192. Min Act: -0.0005

Data Index: 1369547 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0184. Min Act: -0.0005

Data Index: 1638254 (Python Code)

Max Activating Token Index: 225

Text #13

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0173. Min Act: -0.0005

Data Index: 93820 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0191. Min Act: -0.0005

Data Index: 1584465 (Python Code)

Max Activating Token Index: 72

Text #15

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0183. Min Act: -0.0005

Data Index: 1401715 (Python Code)

Max Activating Token Index: 404

Text #16

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0155. Min Act: -0.0005

Data Index: 1595237 (Python Code)

Max Activating Token Index: 835

Text #17

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0186. Min Act: -0.0005

Data Index: 1557763 (Python Code)

Max Activating Token Index: 206

Text #18

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0186. Min Act: -0.0005

Data Index: 1414357 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0187. Min Act: -0.0005

Data Index: 1501035 (Python Code)

Max Activating Token Index: 73