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

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

Neuron 20 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: 0.0291. Min Range: -0.0291

Max Act: 0.0291. Min Act: -0.0006

Data Index: 1305074 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0266. Min Act: -0.0006

Data Index: 709615 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0261. Min Act: -0.0006

Data Index: 388886 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0266. Min Act: -0.0006

Data Index: 111896 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1091057 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1319292 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0261. Min Act: -0.0006

Data Index: 1092179 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1047126 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0241. Min Act: -0.0006

Data Index: 778904 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1243430 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1279536 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0242. Min Act: -0.0006

Data Index: 634846 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0251. Min Act: -0.0006

Data Index: 323428 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0241. Min Act: -0.0006

Data Index: 345562 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0241. Min Act: -0.0006

Data Index: 1331552 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1279547 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0234. Min Act: -0.0006

Data Index: 170378 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1052764 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0244. Min Act: -0.0006

Data Index: 601597 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0250. Min Act: -0.0006

Data Index: 123194 (C4 (Web Text))

Max Activating Token Index: 231