Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1896 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0005

Data Index: 132013 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0170. Min Act: -0.0004

Data Index: 1341465 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0170. Min Act: -0.0005

Data Index: 281490 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0168. Min Act: -0.0004

Data Index: 688135 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0166. Min Act: -0.0005

Data Index: 512520 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0166. Min Act: -0.0004

Data Index: 891486 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0005

Data Index: 879126 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0160. Min Act: -0.0004

Data Index: 1437491 (Python Code)

Max Activating Token Index: 277

Text #8

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0159. Min Act: -0.0004

Data Index: 1475331 (Python Code)

Max Activating Token Index: 192

Text #9

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0159. Min Act: -0.0005

Data Index: 679245 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0159. Min Act: -0.0004

Data Index: 1338894 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0159. Min Act: -0.0004

Data Index: 458251 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0158. Min Act: -0.0004

Data Index: 514734 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0158. Min Act: -0.0004

Data Index: 312271 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0158. Min Act: -0.0004

Data Index: 1574447 (Python Code)

Max Activating Token Index: 417

Text #15

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0156. Min Act: -0.0004

Data Index: 82409 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0154. Min Act: -0.0004

Data Index: 1465292 (Python Code)

Max Activating Token Index: 926

Text #17

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0156. Min Act: -0.0004

Data Index: 1451171 (Python Code)

Max Activating Token Index: 269

Text #18

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0156. Min Act: -0.0004

Data Index: 930372 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0156. Min Act: -0.0004

Data Index: 1541402 (Python Code)

Max Activating Token Index: 515