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

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

Neuron 657 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1456. Min Act: -0.0003

Data Index: 642709 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1466. Min Act: -0.0002

Data Index: 982866 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1460. Min Act: -0.0003

Data Index: 646064 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1329. Min Act: -0.0002

Data Index: 1077884 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1231. Min Act: -0.0002

Data Index: 893659 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1353409 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1307803 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1169. Min Act: -0.0003

Data Index: 659526 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1150. Min Act: -0.0002

Data Index: 603238 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1102. Min Act: -0.0002

Data Index: 515704 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1089. Min Act: -0.0003

Data Index: 461181 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1112. Min Act: -0.0002

Data Index: 174299 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1084. Min Act: -0.0003

Data Index: 1184166 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1072. Min Act: -0.0003

Data Index: 626287 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1176082 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1004. Min Act: -0.0002

Data Index: 848333 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1022. Min Act: -0.0002

Data Index: 690692 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1027. Min Act: -0.0003

Data Index: 59623 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1050. Min Act: -0.0002

Data Index: 296874 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1005. Min Act: -0.0002

Data Index: 941441 (C4 (Web Text))

Max Activating Token Index: 894