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

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

Neuron 3035 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: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0004

Data Index: 1263701 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0239. Min Act: -0.0004

Data Index: 934632 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0240. Min Act: -0.0004

Data Index: 711144 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0233. Min Act: -0.0004

Data Index: 776448 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0218. Min Act: -0.0004

Data Index: 595367 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0227. Min Act: -0.0004

Data Index: 667250 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0219. Min Act: -0.0004

Data Index: 901725 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0214. Min Act: -0.0004

Data Index: 1232800 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0211. Min Act: -0.0004

Data Index: 562882 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0174. Min Act: -0.0004

Data Index: 412245 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0202. Min Act: -0.0004

Data Index: 576456 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0201. Min Act: -0.0004

Data Index: 1190933 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1321930 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0215. Min Act: -0.0004

Data Index: 1144792 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0196. Min Act: -0.0004

Data Index: 1177044 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0181. Min Act: -0.0004

Data Index: 203774 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0198. Min Act: -0.0004

Data Index: 402878 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0209. Min Act: -0.0004

Data Index: 290467 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0218. Min Act: -0.0004

Data Index: 362659 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0191. Min Act: -0.0004

Data Index: 935158 (C4 (Web Text))

Max Activating Token Index: 566