Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 468 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0222. Min Act: -0.0002

Data Index: 664404 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0208. Min Act: -0.0002

Data Index: 90141 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1053731 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0169. Min Act: -0.0002

Data Index: 369522 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0178. Min Act: -0.0001

Data Index: 636021 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0177. Min Act: -0.0001

Data Index: 838210 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0149. Min Act: -0.0002

Data Index: 645829 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0157. Min Act: -0.0002

Data Index: 340013 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1198117 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0164. Min Act: -0.0002

Data Index: 647463 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0162. Min Act: -0.0001

Data Index: 58042 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0147. Min Act: -0.0002

Data Index: 314818 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0152. Min Act: -0.0002

Data Index: 53902 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0153. Min Act: -0.0001

Data Index: 53706 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1072175 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0147. Min Act: -0.0001

Data Index: 978418 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0149. Min Act: -0.0001

Data Index: 258423 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1173455 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0158. Min Act: -0.0001

Data Index: 137015 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0145. Min Act: -0.0001

Data Index: 434995 (C4 (Web Text))

Max Activating Token Index: 95