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

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

Neuron 1983 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: 0.0197. Min Range: -0.0197

Max Act: 0.0197. Min Act: -0.0005

Data Index: 657856 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0189. Min Act: -0.0006

Data Index: 112652 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1358166 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0186. Min Act: -0.0006

Data Index: 343547 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0189. Min Act: -0.0006

Data Index: 958124 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0179. Min Act: -0.0006

Data Index: 575993 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1324281 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0181. Min Act: -0.0006

Data Index: 238320 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0175. Min Act: -0.0006

Data Index: 169606 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0170. Min Act: -0.0006

Data Index: 873241 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0170. Min Act: -0.0006

Data Index: 411489 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0169. Min Act: -0.0006

Data Index: 814377 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1335746 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0169. Min Act: -0.0006

Data Index: 344489 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0169. Min Act: -0.0005

Data Index: 1541116 (Python Code)

Max Activating Token Index: 932

Text #15

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0171. Min Act: -0.0005

Data Index: 411180 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0167. Min Act: -0.0006

Data Index: 99017 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1195127 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0166. Min Act: -0.0006

Data Index: 757726 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0166. Min Act: -0.0006

Data Index: 986721 (C4 (Web Text))

Max Activating Token Index: 703