Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1596 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0856. Min Act: -0.0002

Data Index: 999212 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0890. Min Act: -0.0002

Data Index: 981532 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0922. Min Act: -0.0002

Data Index: 696048 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0865. Min Act: -0.0002

Data Index: 971332 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1272958 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0853. Min Act: -0.0002

Data Index: 492116 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0829. Min Act: -0.0002

Data Index: 474786 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1209164 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1165330 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0728. Min Act: -0.0002

Data Index: 231069 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0738. Min Act: -0.0002

Data Index: 539608 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1011439 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0687. Min Act: -0.0002

Data Index: 30870 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1183611 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0691. Min Act: -0.0002

Data Index: 976840 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0671. Min Act: -0.0002

Data Index: 547984 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0647. Min Act: -0.0002

Data Index: 376266 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1097759 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0656. Min Act: -0.0002

Data Index: 669594 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0645. Min Act: -0.0002

Data Index: 739519 (C4 (Web Text))

Max Activating Token Index: 767