Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3182 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0422. Min Act: -0.0002

Data Index: 384535 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1194499 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0317. Min Act: -0.0002

Data Index: 560837 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0283. Min Act: -0.0002

Data Index: 590366 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1049635 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1019738 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0235. Min Act: -0.0002

Data Index: 521729 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1349708 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0250. Min Act: -0.0002

Data Index: 723683 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0233. Min Act: -0.0002

Data Index: 663579 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1529890 (Python Code)

Max Activating Token Index: 60

Text #11

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1318818 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1531533 (Python Code)

Max Activating Token Index: 319

Text #13

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0217. Min Act: -0.0002

Data Index: 16296 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0190. Min Act: -0.0002

Data Index: 519145 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1481938 (Python Code)

Max Activating Token Index: 19

Text #16

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1069926 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1634559 (Python Code)

Max Activating Token Index: 929

Text #18

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1632175 (Python Code)

Max Activating Token Index: 243

Text #19

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1125377 (C4 (Web Text))

Max Activating Token Index: 998