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

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

Neuron 539 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: 2.5578. Min Range: -2.5578

Max Act: 2.5578. Min Act: -0.0000

Data Index: 886993 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 2.5578. Min Range: -2.5578

Max Act: 2.2491. Min Act: -0.0000

Data Index: 127660 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 2.5578. Min Range: -2.5578

Max Act: 2.1689. Min Act: -0.0000

Data Index: 999483 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 2.5578. Min Range: -2.5578

Max Act: 2.0061. Min Act: -0.0000

Data Index: 1296762 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 2.5578. Min Range: -2.5578

Max Act: 2.0708. Min Act: -0.0000

Data Index: 351017 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 2.5578. Min Range: -2.5578

Max Act: 2.1785. Min Act: -0.0000

Data Index: 434281 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 2.5578. Min Range: -2.5578

Max Act: 2.0454. Min Act: -0.0000

Data Index: 129661 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 2.5578. Min Range: -2.5578

Max Act: 2.0026. Min Act: -0.0000

Data Index: 345367 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 2.5578. Min Range: -2.5578

Max Act: 1.9967. Min Act: -0.0000

Data Index: 1023457 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 2.5578. Min Range: -2.5578

Max Act: 1.9735. Min Act: -0.0000

Data Index: 632174 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 2.5578. Min Range: -2.5578

Max Act: 2.0255. Min Act: -0.0000

Data Index: 593940 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 2.5578. Min Range: -2.5578

Max Act: 1.9346. Min Act: -0.0000

Data Index: 13593 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 2.5578. Min Range: -2.5578

Max Act: 1.9236. Min Act: -0.0000

Data Index: 635623 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 2.5578. Min Range: -2.5578

Max Act: 1.9313. Min Act: -0.0000

Data Index: 512049 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 2.5578. Min Range: -2.5578

Max Act: 1.9101. Min Act: -0.0000

Data Index: 748500 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 2.5578. Min Range: -2.5578

Max Act: 1.9083. Min Act: -0.0000

Data Index: 545751 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 2.5578. Min Range: -2.5578

Max Act: 1.8050. Min Act: -0.0000

Data Index: 721296 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 2.5578. Min Range: -2.5578

Max Act: 1.8999. Min Act: -0.0000

Data Index: 3919 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 2.5578. Min Range: -2.5578

Max Act: 1.7857. Min Act: -0.0000

Data Index: 905446 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 2.5578. Min Range: -2.5578

Max Act: 1.8803. Min Act: -0.0000

Data Index: 196458 (C4 (Web Text))

Max Activating Token Index: 707