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

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

Neuron 3759 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: 1.7913. Min Range: -1.7913

Max Act: 1.7231. Min Act: -0.0000

Data Index: 869497 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.7039. Min Act: -0.0000

Data Index: 429041 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.7913. Min Act: -0.0000

Data Index: 980409 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.5581. Min Act: -0.0000

Data Index: 834788 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.4579. Min Act: -0.0000

Data Index: 431502 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.3963. Min Act: -0.0000

Data Index: 1127418 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.3475. Min Act: -0.0000

Data Index: 572329 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.3346. Min Act: -0.0000

Data Index: 554078 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.2646. Min Act: -0.0000

Data Index: 440028 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.2695. Min Act: -0.0000

Data Index: 518553 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1182626 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.2252. Min Act: -0.0000

Data Index: 326226 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1338956 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.0780. Min Act: -0.0000

Data Index: 1058540 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.1697. Min Act: -0.0000

Data Index: 143952 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.1431. Min Act: -0.0000

Data Index: 775366 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.0953. Min Act: -0.0000

Data Index: 107661 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1122061 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1611148 (Python Code)

Max Activating Token Index: 784

Text #19

Max Range: 1.7913. Min Range: -1.7913

Max Act: 0.9879. Min Act: -0.0000

Data Index: 518743 (C4 (Web Text))

Max Activating Token Index: 176