Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1252 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0231. Min Act: -0.0006

Data Index: 595281 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0006

Data Index: 470426 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0202. Min Act: -0.0006

Data Index: 300039 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0212. Min Act: -0.0006

Data Index: 556361 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0194. Min Act: -0.0005

Data Index: 677766 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0201. Min Act: -0.0006

Data Index: 1512257 (Python Code)

Max Activating Token Index: 361

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0195. Min Act: -0.0005

Data Index: 936343 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0191. Min Act: -0.0006

Data Index: 334586 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1270456 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1253642 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1429544 (Python Code)

Max Activating Token Index: 539

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1485209 (Python Code)

Max Activating Token Index: 615

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0183. Min Act: -0.0005

Data Index: 119841 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0187. Min Act: -0.0006

Data Index: 893873 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0187. Min Act: -0.0005

Data Index: 236355 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0189. Min Act: -0.0005

Data Index: 297485 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0185. Min Act: -0.0005

Data Index: 40545 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0184. Min Act: -0.0006

Data Index: 931504 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1385307 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0185. Min Act: -0.0005

Data Index: 1252877 (C4 (Web Text))

Max Activating Token Index: 852