Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5604 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0559. Min Range: -1.0559

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1134986 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1141225 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 1.0559. Min Range: -1.0559

Max Act: 1.0293. Min Act: -0.0000

Data Index: 761086 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.0559. Min Range: -1.0559

Max Act: 1.0559. Min Act: -0.0000

Data Index: 189486 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1155162 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.9385. Min Act: -0.0000

Data Index: 738269 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.9175. Min Act: -0.0000

Data Index: 1156123 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.8953. Min Act: -0.0000

Data Index: 94491 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.8926. Min Act: -0.0000

Data Index: 944078 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.7578. Min Act: -0.0000

Data Index: 846796 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1336239 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1035036 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.8113. Min Act: 0.0000

Data Index: 456401 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1329589 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.7876. Min Act: -0.0000

Data Index: 695751 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.7809. Min Act: 0.0000

Data Index: 825236 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1091205 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.7305. Min Act: -0.0000

Data Index: 686737 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.7228. Min Act: -0.0000

Data Index: 466773 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 1.0559. Min Range: -1.0559

Max Act: 0.7641. Min Act: 0.0000

Data Index: 734013 (C4 (Web Text))

Max Activating Token Index: 883