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

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

Neuron 1609 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1363. Min Act: -0.0000

Data Index: 785009 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1284. Min Act: -0.0000

Data Index: 421357 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1277. Min Act: -0.0000

Data Index: 183460 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1058961 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1310. Min Act: -0.0000

Data Index: 423826 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1241920 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1224751 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1238. Min Act: -0.0000

Data Index: 282554 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1128. Min Act: -0.0000

Data Index: 909008 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1241. Min Act: -0.0000

Data Index: 4499 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1238. Min Act: -0.0000

Data Index: 232670 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1229. Min Act: -0.0000

Data Index: 586984 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1317069 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1164. Min Act: -0.0000

Data Index: 462620 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1048. Min Act: -0.0000

Data Index: 171030 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1061. Min Act: -0.0000

Data Index: 28055 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1062. Min Act: -0.0000

Data Index: 162996 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1054. Min Act: -0.0000

Data Index: 743923 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1133488 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1090. Min Act: -0.0000

Data Index: 557552 (C4 (Web Text))

Max Activating Token Index: 429