Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1355 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1180729 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1340. Min Act: -0.0002

Data Index: 72920 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1018808 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1244. Min Act: -0.0002

Data Index: 974702 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1383. Min Act: -0.0002

Data Index: 611294 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1190. Min Act: -0.0002

Data Index: 759992 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1232. Min Act: -0.0002

Data Index: 217427 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1070. Min Act: -0.0002

Data Index: 249022 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1258. Min Act: -0.0002

Data Index: 533336 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1257. Min Act: -0.0002

Data Index: 977379 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1105. Min Act: -0.0002

Data Index: 329808 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1184. Min Act: -0.0002

Data Index: 1353543 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1094438 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1071. Min Act: -0.0002

Data Index: 414762 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1328. Min Act: -0.0002

Data Index: 839183 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1138. Min Act: -0.0002

Data Index: 523972 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0994. Min Act: -0.0002

Data Index: 140151 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1076. Min Act: -0.0002

Data Index: 1136885 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1039. Min Act: -0.0002

Data Index: 346119 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1071. Min Act: -0.0002

Data Index: 466480 (C4 (Web Text))

Max Activating Token Index: 528