Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 666 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1302. Min Act: -0.0003

Data Index: 1079758 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1305. Min Act: -0.0001

Data Index: 335163 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1226. Min Act: -0.0003

Data Index: 1137935 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1295. Min Act: -0.0003

Data Index: 694063 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1234. Min Act: -0.0003

Data Index: 720615 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1216. Min Act: -0.0001

Data Index: 69745 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1206. Min Act: -0.0000

Data Index: 756669 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1186. Min Act: -0.0001

Data Index: 780770 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1142. Min Act: -0.0002

Data Index: 779324 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1169. Min Act: -0.0003

Data Index: 527362 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1175. Min Act: -0.0002

Data Index: 1162345 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1139. Min Act: -0.0002

Data Index: 858440 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1115. Min Act: -0.0003

Data Index: 1455354 (Python Code)

Max Activating Token Index: 877

Text #13

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1133. Min Act: -0.0002

Data Index: 460747 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1130. Min Act: -0.0002

Data Index: 1125278 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1119. Min Act: -0.0003

Data Index: 173167 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1116. Min Act: -0.0003

Data Index: 1355994 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1114. Min Act: -0.0002

Data Index: 554105 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1164. Min Act: -0.0002

Data Index: 201019 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1109. Min Act: -0.0001

Data Index: 449857 (C4 (Web Text))

Max Activating Token Index: 664