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

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

Neuron 2017 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0183. Min Act: -0.0006

Data Index: 275399 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0183. Min Act: -0.0006

Data Index: 279093 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0180. Min Act: -0.0006

Data Index: 23092 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0176. Min Act: -0.0006

Data Index: 635632 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1137547 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0175. Min Act: -0.0006

Data Index: 830859 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1065631 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0163. Min Act: -0.0006

Data Index: 992987 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0160. Min Act: -0.0006

Data Index: 795434 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1264650 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0154. Min Act: -0.0007

Data Index: 392589 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1184354 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0158. Min Act: -0.0006

Data Index: 104180 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1254817 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0153. Min Act: -0.0006

Data Index: 861915 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0149. Min Act: -0.0006

Data Index: 745915 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0149. Min Act: -0.0006

Data Index: 159275 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0150. Min Act: -0.0006

Data Index: 336685 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0148. Min Act: -0.0006

Data Index: 719565 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0151. Min Act: -0.0006

Data Index: 414023 (C4 (Web Text))

Max Activating Token Index: 846