Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 726 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0004

Data Index: 58671 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0269. Min Act: -0.0004

Data Index: 62819 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0241. Min Act: -0.0004

Data Index: 845675 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0252. Min Act: -0.0004

Data Index: 1138288 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0236. Min Act: -0.0004

Data Index: 832075 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0229. Min Act: -0.0004

Data Index: 199709 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0229. Min Act: -0.0004

Data Index: 523588 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0232. Min Act: -0.0004

Data Index: 493458 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0228. Min Act: -0.0004

Data Index: 998131 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1000677 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0221. Min Act: -0.0004

Data Index: 540203 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0228. Min Act: -0.0004

Data Index: 1071575 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0229. Min Act: -0.0004

Data Index: 1083487 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0214. Min Act: -0.0004

Data Index: 913237 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0214. Min Act: -0.0004

Data Index: 982147 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0219. Min Act: -0.0004

Data Index: 855999 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0209. Min Act: -0.0004

Data Index: 413673 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0217. Min Act: -0.0004

Data Index: 1036811 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0224. Min Act: -0.0004

Data Index: 879432 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0224. Min Act: -0.0004

Data Index: 931450 (C4 (Web Text))

Max Activating Token Index: 132