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

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

Neuron 3773 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: 0.1325. Min Range: -0.1325

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1490358 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1325. Min Act: -0.0000

Data Index: 191722 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1230. Min Act: -0.0000

Data Index: 52736 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1216. Min Act: -0.0000

Data Index: 579834 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1192. Min Act: -0.0000

Data Index: 389963 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1178. Min Act: -0.0000

Data Index: 166314 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1174. Min Act: -0.0000

Data Index: 860661 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1104. Min Act: -0.0000

Data Index: 888520 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1060. Min Act: -0.0000

Data Index: 412618 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1101. Min Act: -0.0000

Data Index: 130033 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1126. Min Act: -0.0000

Data Index: 788383 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1023. Min Act: -0.0000

Data Index: 751645 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1220653 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1226768 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1017. Min Act: -0.0000

Data Index: 352198 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1049. Min Act: -0.0000

Data Index: 334513 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.0971. Min Act: -0.0000

Data Index: 621563 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.1003. Min Act: -0.0000

Data Index: 511611 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1141358 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.1325. Min Range: -0.1325

Max Act: 0.0998. Min Act: -0.0000

Data Index: 633174 (C4 (Web Text))

Max Activating Token Index: 906