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

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

Neuron 2771 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.2572. Min Act: -0.0000

Data Index: 695728 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.1638. Min Act: -0.0000

Data Index: 1236158 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.0041. Min Act: -0.0000

Data Index: 209495 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9823. Min Act: -0.0000

Data Index: 450081 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.0057. Min Act: -0.0000

Data Index: 668774 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1345871 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9585. Min Act: -0.0000

Data Index: 350089 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 1.2572. Min Range: -1.2572

Max Act: 1.0022. Min Act: -0.0000

Data Index: 471214 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9794. Min Act: -0.0000

Data Index: 766943 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8826. Min Act: -0.0000

Data Index: 37008 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8972. Min Act: -0.0000

Data Index: 127711 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9001. Min Act: -0.0000

Data Index: 1198198 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8654. Min Act: -0.0000

Data Index: 710703 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1136173 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.9185. Min Act: 0.0000

Data Index: 102121 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1594868 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8518. Min Act: -0.0000

Data Index: 559966 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8941. Min Act: 0.0000

Data Index: 136631 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1348674 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 1.2572. Min Range: -1.2572

Max Act: 0.8200. Min Act: 0.0000

Data Index: 931945 (C4 (Web Text))

Max Activating Token Index: 370