Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2569 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1567. Min Act: -0.0001

Data Index: 767871 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1450. Min Act: -0.0001

Data Index: 83613 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1219. Min Act: -0.0001

Data Index: 622647 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1244. Min Act: -0.0001

Data Index: 478618 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1185. Min Act: -0.0001

Data Index: 696454 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1178. Min Act: -0.0001

Data Index: 609554 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1221. Min Act: -0.0001

Data Index: 10531 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1211479 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1337104 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1202. Min Act: -0.0001

Data Index: 449909 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1156. Min Act: -0.0001

Data Index: 861179 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1124. Min Act: -0.0001

Data Index: 253197 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1167. Min Act: -0.0001

Data Index: 63248 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1157. Min Act: -0.0001

Data Index: 565846 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1358914 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1195. Min Act: -0.0001

Data Index: 123342 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1109. Min Act: -0.0001

Data Index: 847849 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1323665 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1090. Min Act: -0.0001

Data Index: 188981 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1171. Min Act: -0.0001

Data Index: 810069 (C4 (Web Text))

Max Activating Token Index: 641