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

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

Neuron 1064 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: 0.0203. Min Range: -0.0203

Max Act: 0.0203. Min Act: -0.0006

Data Index: 156070 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0174. Min Act: -0.0006

Data Index: 320241 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1505294 (Python Code)

Max Activating Token Index: 404

Text #3

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0176. Min Act: -0.0006

Data Index: 798515 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0179. Min Act: -0.0006

Data Index: 339890 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0172. Min Act: -0.0006

Data Index: 261334 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0163. Min Act: -0.0006

Data Index: 837649 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1326910 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0169. Min Act: -0.0006

Data Index: 366726 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1168969 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1328875 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0167. Min Act: -0.0006

Data Index: 345475 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1304230 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0166. Min Act: -0.0006

Data Index: 518405 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0162. Min Act: -0.0006

Data Index: 308614 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0180. Min Act: -0.0006

Data Index: 827888 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0160. Min Act: -0.0006

Data Index: 73557 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0159. Min Act: -0.0006

Data Index: 566598 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0159. Min Act: -0.0006

Data Index: 628385 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0152. Min Act: -0.0006

Data Index: 679016 (C4 (Web Text))

Max Activating Token Index: 753