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

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

Neuron 888 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: 0.1560. Min Range: -0.1560

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1249761 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1338556 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1391. Min Act: -0.0001

Data Index: 612928 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1320. Min Act: -0.0001

Data Index: 831111 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1118. Min Act: -0.0001

Data Index: 92056 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1258. Min Act: -0.0001

Data Index: 738530 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1235. Min Act: -0.0001

Data Index: 712779 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1236. Min Act: -0.0001

Data Index: 304530 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1176. Min Act: -0.0001

Data Index: 226958 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1170. Min Act: -0.0001

Data Index: 358675 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1028. Min Act: -0.0001

Data Index: 617259 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1242. Min Act: -0.0001

Data Index: 996312 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1343024 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1150. Min Act: -0.0001

Data Index: 444547 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1136. Min Act: -0.0001

Data Index: 715232 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1172707 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1142. Min Act: -0.0001

Data Index: 214756 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1216. Min Act: -0.0001

Data Index: 700389 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1131. Min Act: -0.0001

Data Index: 602387 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1136. Min Act: -0.0001

Data Index: 148525 (C4 (Web Text))

Max Activating Token Index: 861