Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2704 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1251584 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1343. Min Act: -0.0000

Data Index: 660737 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1303. Min Act: -0.0000

Data Index: 604180 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1266. Min Act: -0.0000

Data Index: 935407 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1275. Min Act: -0.0001

Data Index: 445044 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1266. Min Act: -0.0000

Data Index: 326442 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1199. Min Act: -0.0000

Data Index: 59551 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1239. Min Act: -0.0000

Data Index: 1298979 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1188873 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1253. Min Act: -0.0000

Data Index: 67756 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1169. Min Act: -0.0000

Data Index: 743030 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1214. Min Act: -0.0000

Data Index: 48541 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1162. Min Act: -0.0000

Data Index: 464739 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1296474 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1156. Min Act: -0.0000

Data Index: 329446 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1114. Min Act: -0.0000

Data Index: 771565 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1149. Min Act: -0.0001

Data Index: 700789 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1101. Min Act: -0.0000

Data Index: 39038 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1059935 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1099. Min Act: -0.0000

Data Index: 213710 (C4 (Web Text))

Max Activating Token Index: 442