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

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

Neuron 735 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0207. Min Act: -0.0003

Data Index: 601271 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0190. Min Act: -0.0003

Data Index: 861943 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0194. Min Act: -0.0003

Data Index: 1556169 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1043508 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1068470 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1001962 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0185. Min Act: -0.0003

Data Index: 327046 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0187. Min Act: -0.0003

Data Index: 944214 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0180. Min Act: -0.0003

Data Index: 482640 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0181. Min Act: -0.0003

Data Index: 579624 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0178. Min Act: -0.0003

Data Index: 699100 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1390216 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1441609 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0188. Min Act: -0.0003

Data Index: 722831 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0170. Min Act: -0.0003

Data Index: 681407 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0173. Min Act: -0.0003

Data Index: 247207 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1349117 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0172. Min Act: -0.0003

Data Index: 732097 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0168. Min Act: -0.0003

Data Index: 428841 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1331776 (C4 (Web Text))

Max Activating Token Index: 575