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

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

Neuron 1065 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0809. Min Act: -0.0002

Data Index: 944152 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0698. Min Act: -0.0002

Data Index: 78903 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0745. Min Act: -0.0002

Data Index: 510758 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0717. Min Act: -0.0002

Data Index: 977687 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0645. Min Act: -0.0002

Data Index: 205787 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0601. Min Act: -0.0002

Data Index: 734589 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0651. Min Act: -0.0002

Data Index: 317460 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0694. Min Act: -0.0002

Data Index: 902283 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1074337 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0514. Min Act: -0.0002

Data Index: 16592 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0662. Min Act: -0.0002

Data Index: 932392 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0728. Min Act: -0.0002

Data Index: 380304 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0634. Min Act: -0.0002

Data Index: 846542 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0607. Min Act: -0.0002

Data Index: 262437 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0610. Min Act: -0.0002

Data Index: 516861 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0602. Min Act: -0.0002

Data Index: 572545 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1150944 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0576. Min Act: -0.0002

Data Index: 604107 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0602. Min Act: -0.0002

Data Index: 130819 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1117502 (C4 (Web Text))

Max Activating Token Index: 91