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

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

Neuron 4765 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: 0.7071. Min Range: -0.7071

Max Act: 0.7071. Min Act: -0.0000

Data Index: 405020 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1256750 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6564. Min Act: -0.0000

Data Index: 785958 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6052. Min Act: -0.0000

Data Index: 920986 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6181. Min Act: -0.0000

Data Index: 628952 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6007. Min Act: -0.0000

Data Index: 326808 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5952. Min Act: -0.0000

Data Index: 726244 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6164. Min Act: -0.0000

Data Index: 448662 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1332134 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5767. Min Act: -0.0000

Data Index: 479182 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5759. Min Act: -0.0000

Data Index: 912890 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5706. Min Act: -0.0000

Data Index: 504529 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1128505 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5620. Min Act: -0.0000

Data Index: 480540 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5639. Min Act: -0.0000

Data Index: 558126 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5521. Min Act: -0.0000

Data Index: 263933 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5487. Min Act: -0.0000

Data Index: 892422 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5461. Min Act: -0.0000

Data Index: 944064 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5425. Min Act: -0.0000

Data Index: 336260 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1039371 (C4 (Web Text))

Max Activating Token Index: 539