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

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

Neuron 1219 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0249. Min Act: -0.0005

Data Index: 804722 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0194. Min Act: -0.0005

Data Index: 388214 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0192. Min Act: -0.0004

Data Index: 1122042 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0186. Min Act: -0.0005

Data Index: 854103 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0188. Min Act: -0.0004

Data Index: 132383 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0179. Min Act: -0.0005

Data Index: 845738 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0185. Min Act: -0.0004

Data Index: 270370 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0183. Min Act: -0.0005

Data Index: 918054 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0170. Min Act: -0.0005

Data Index: 1229138 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0167. Min Act: -0.0004

Data Index: 876167 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0168. Min Act: -0.0005

Data Index: 765907 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0169. Min Act: -0.0005

Data Index: 462408 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0158. Min Act: -0.0005

Data Index: 48327 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0150. Min Act: -0.0005

Data Index: 702427 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0145. Min Act: -0.0004

Data Index: 18628 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0151. Min Act: -0.0004

Data Index: 607186 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0158. Min Act: -0.0005

Data Index: 380553 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0149. Min Act: -0.0005

Data Index: 834473 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0154. Min Act: -0.0004

Data Index: 1399501 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0150. Min Act: -0.0005

Data Index: 385124 (C4 (Web Text))

Max Activating Token Index: 333