Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5245 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1385. Min Act: -0.0000

Data Index: 727772 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1452. Min Act: -0.0000

Data Index: 518734 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1281481 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1375. Min Act: -0.0000

Data Index: 575775 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1054484 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1156. Min Act: -0.0000

Data Index: 94386 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1214. Min Act: -0.0000

Data Index: 829934 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1224. Min Act: -0.0000

Data Index: 703031 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1224. Min Act: -0.0000

Data Index: 793516 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1173. Min Act: -0.0000

Data Index: 202346 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1183. Min Act: -0.0000

Data Index: 921294 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1102. Min Act: -0.0000

Data Index: 816399 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1343187 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1124. Min Act: -0.0000

Data Index: 349143 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1045. Min Act: -0.0000

Data Index: 354034 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1156176 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1111. Min Act: 0.0001

Data Index: 444332 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1302491 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1134. Min Act: -0.0000

Data Index: 16296 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1026. Min Act: -0.0000

Data Index: 934504 (C4 (Web Text))

Max Activating Token Index: 30