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

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

Neuron 183 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1435. Min Act: -0.0003

Data Index: 1144632 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1459. Min Act: -0.0003

Data Index: 856681 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1272. Min Act: -0.0003

Data Index: 615378 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1426. Min Act: -0.0003

Data Index: 690077 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1210. Min Act: -0.0003

Data Index: 1007947 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1256. Min Act: -0.0003

Data Index: 681189 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1244. Min Act: -0.0003

Data Index: 1077793 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1238. Min Act: -0.0003

Data Index: 1164763 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1260. Min Act: -0.0003

Data Index: 478806 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1219. Min Act: -0.0003

Data Index: 211029 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.0968. Min Act: -0.0003

Data Index: 602101 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1210. Min Act: -0.0003

Data Index: 118545 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1121. Min Act: -0.0003

Data Index: 191758 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1166. Min Act: -0.0003

Data Index: 1352540 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1108. Min Act: -0.0003

Data Index: 172597 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1139. Min Act: -0.0003

Data Index: 1153755 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1085. Min Act: -0.0003

Data Index: 839973 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1102. Min Act: -0.0003

Data Index: 580357 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1146. Min Act: -0.0003

Data Index: 909160 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1066. Min Act: -0.0003

Data Index: 384655 (C4 (Web Text))

Max Activating Token Index: 792