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

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

Neuron 136 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: 0.0194. Min Range: -0.0194

Max Act: 0.0179. Min Act: -0.0005

Data Index: 1494016 (Python Code)

Max Activating Token Index: 483

Text #1

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0186. Min Act: -0.0005

Data Index: 991423 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0182. Min Act: -0.0005

Data Index: 910597 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0180. Min Act: -0.0005

Data Index: 686233 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0194. Min Act: -0.0005

Data Index: 1055429 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0177. Min Act: -0.0005

Data Index: 1238426 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0183. Min Act: -0.0005

Data Index: 1160434 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0182. Min Act: -0.0005

Data Index: 1113141 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0183. Min Act: -0.0005

Data Index: 631811 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0186. Min Act: -0.0005

Data Index: 970430 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0177. Min Act: -0.0005

Data Index: 359655 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0172. Min Act: -0.0005

Data Index: 1118575 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0184. Min Act: -0.0005

Data Index: 262731 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0176. Min Act: -0.0005

Data Index: 725581 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0174. Min Act: -0.0005

Data Index: 824991 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0172. Min Act: -0.0005

Data Index: 1307566 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0174. Min Act: -0.0005

Data Index: 496851 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0164. Min Act: -0.0005

Data Index: 1121091 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0170. Min Act: -0.0005

Data Index: 1096967 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0166. Min Act: -0.0005

Data Index: 619298 (C4 (Web Text))

Max Activating Token Index: 99