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

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

Neuron 15 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: 0.3820. Min Range: -0.3820

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1029853 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3316. Min Act: -0.0000

Data Index: 778382 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3820. Min Act: -0.0000

Data Index: 479314 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1253462 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1368995 (Python Code)

Max Activating Token Index: 860

Text #5

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3315. Min Act: -0.0000

Data Index: 765951 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3035. Min Act: -0.0000

Data Index: 820720 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2911. Min Act: -0.0000

Data Index: 225910 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3117. Min Act: -0.0000

Data Index: 289578 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1022538 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3093. Min Act: -0.0000

Data Index: 848524 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1038347 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3052. Min Act: -0.0000

Data Index: 893266 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1618432 (Python Code)

Max Activating Token Index: 983

Text #14

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2925. Min Act: -0.0000

Data Index: 603184 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2867. Min Act: -0.0000

Data Index: 444862 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2968. Min Act: -0.0000

Data Index: 153075 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2955. Min Act: -0.0000

Data Index: 390621 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2926. Min Act: -0.0000

Data Index: 92103 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3021. Min Act: -0.0000

Data Index: 254233 (C4 (Web Text))

Max Activating Token Index: 938