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

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

Neuron 296 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0886. Min Act: -0.0002

Data Index: 532587 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0839. Min Act: -0.0002

Data Index: 134307 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0807. Min Act: -0.0002

Data Index: 946446 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1223026 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0804. Min Act: -0.0002

Data Index: 113728 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0745. Min Act: -0.0002

Data Index: 322737 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0745. Min Act: -0.0002

Data Index: 127433 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0767. Min Act: -0.0002

Data Index: 349640 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0742. Min Act: -0.0002

Data Index: 83287 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0735. Min Act: -0.0002

Data Index: 642430 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0731. Min Act: -0.0002

Data Index: 464189 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0695. Min Act: -0.0002

Data Index: 602705 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0712. Min Act: -0.0002

Data Index: 864823 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0707. Min Act: -0.0002

Data Index: 656092 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1243805 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0688. Min Act: -0.0002

Data Index: 864989 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0659. Min Act: -0.0002

Data Index: 642870 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1019818 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0711. Min Act: -0.0002

Data Index: 694228 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1331084 (C4 (Web Text))

Max Activating Token Index: 590