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

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

Neuron 2135 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: 0.1380. Min Range: -0.1380

Max Act: 0.1380. Min Act: -0.0001

Data Index: 444160 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1274. Min Act: -0.0001

Data Index: 862018 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1224. Min Act: -0.0001

Data Index: 528285 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1071199 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1176. Min Act: -0.0001

Data Index: 114656 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1180. Min Act: -0.0001

Data Index: 532080 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1135. Min Act: -0.0001

Data Index: 421832 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1277387 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1143. Min Act: -0.0001

Data Index: 657347 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1087062 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1340666 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1168. Min Act: -0.0001

Data Index: 763673 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1119. Min Act: -0.0001

Data Index: 435789 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1163. Min Act: -0.0001

Data Index: 834487 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1111. Min Act: -0.0001

Data Index: 515708 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1106. Min Act: -0.0001

Data Index: 755598 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1091. Min Act: -0.0001

Data Index: 256584 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1019. Min Act: -0.0001

Data Index: 742707 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1090809 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1055. Min Act: -0.0001

Data Index: 76692 (C4 (Web Text))

Max Activating Token Index: 454