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

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

Neuron 5090 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: 0.5952. Min Range: -0.5952

Max Act: 0.5952. Min Act: -0.0000

Data Index: 781924 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.5833. Min Act: -0.0000

Data Index: 730259 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.5528. Min Act: -0.0000

Data Index: 969715 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.5098. Min Act: -0.0000

Data Index: 319122 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1141676 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.5211. Min Act: -0.0000

Data Index: 422251 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1156660 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4975. Min Act: -0.0000

Data Index: 188556 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4842. Min Act: -0.0000

Data Index: 677979 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4961. Min Act: -0.0000

Data Index: 6094 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4688. Min Act: -0.0000

Data Index: 488105 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1333291 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1251154 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4466. Min Act: -0.0000

Data Index: 957374 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4601. Min Act: -0.0000

Data Index: 534043 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4426. Min Act: -0.0000

Data Index: 377145 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4549. Min Act: -0.0000

Data Index: 854356 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4663. Min Act: -0.0000

Data Index: 985377 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4176. Min Act: -0.0000

Data Index: 657031 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1118222 (C4 (Web Text))

Max Activating Token Index: 150