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

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

Neuron 2464 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1575. Min Act: -0.0000

Data Index: 746729 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1503. Min Act: -0.0000

Data Index: 426856 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1385. Min Act: -0.0000

Data Index: 636782 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1372. Min Act: -0.0000

Data Index: 189987 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1323. Min Act: -0.0000

Data Index: 748729 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1215368 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1240. Min Act: -0.0000

Data Index: 188458 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1265930 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1237. Min Act: -0.0000

Data Index: 506608 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1198. Min Act: -0.0000

Data Index: 33910 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1090. Min Act: -0.0000

Data Index: 180339 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1026623 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1079. Min Act: -0.0000

Data Index: 47660 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1101. Min Act: -0.0000

Data Index: 649883 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1053. Min Act: -0.0000

Data Index: 645651 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1028. Min Act: -0.0000

Data Index: 951861 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1051. Min Act: -0.0000

Data Index: 119161 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1087384 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1337291 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1004. Min Act: -0.0000

Data Index: 538857 (C4 (Web Text))

Max Activating Token Index: 666