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

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

Neuron 5480 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3697. Min Range: -5.3697

Max Act: 5.3697. Min Act: -0.0000

Data Index: 515943 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.9636. Min Act: -0.0000

Data Index: 399603 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 5.3697. Min Range: -5.3697

Max Act: 5.2250. Min Act: -0.0000

Data Index: 1227974 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.8928. Min Act: -0.0000

Data Index: 568757 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 5.3697. Min Range: -5.3697

Max Act: 5.0448. Min Act: -0.0000

Data Index: 773190 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.4982. Min Act: -0.0000

Data Index: 113180 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.4595. Min Act: -0.0000

Data Index: 1173530 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.4185. Min Act: -0.0000

Data Index: 1191510 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.3564. Min Act: -0.0000

Data Index: 890964 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.4564. Min Act: -0.0000

Data Index: 399174 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.3651. Min Act: -0.0000

Data Index: 78661 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.3419. Min Act: -0.0000

Data Index: 1207920 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.3270. Min Act: -0.0000

Data Index: 387920 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.1580. Min Act: -0.0000

Data Index: 1146235 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.5056. Min Act: -0.0000

Data Index: 280647 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.2492. Min Act: -0.0000

Data Index: 571121 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.0604. Min Act: -0.0000

Data Index: 1238667 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.2042. Min Act: -0.0000

Data Index: 1289982 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 5.3697. Min Range: -5.3697

Max Act: 3.9821. Min Act: -0.0000

Data Index: 783417 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 5.3697. Min Range: -5.3697

Max Act: 4.3412. Min Act: -0.0000

Data Index: 1122733 (C4 (Web Text))

Max Activating Token Index: 509