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

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

Neuron 5092 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: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1289368 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1611847 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1300768 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0563. Min Act: -0.0002

Data Index: 750814 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0550. Min Act: -0.0002

Data Index: 875246 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0535. Min Act: -0.0002

Data Index: 122205 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0515. Min Act: -0.0002

Data Index: 771611 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0479. Min Act: -0.0002

Data Index: 190365 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0494. Min Act: -0.0002

Data Index: 364197 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0565. Min Act: -0.0002

Data Index: 492840 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0543. Min Act: -0.0002

Data Index: 833810 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1208004 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0515. Min Act: -0.0002

Data Index: 218528 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1322259 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1557781 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0505. Min Act: -0.0002

Data Index: 694059 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0549. Min Act: -0.0002

Data Index: 570609 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0543. Min Act: -0.0002

Data Index: 872597 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1088730 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0483. Min Act: -0.0002

Data Index: 324853 (C4 (Web Text))

Max Activating Token Index: 403