Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3108 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.3438. Min Act: -0.0001

Data Index: 912880 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.3268. Min Act: -0.0001

Data Index: 331561 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2749. Min Act: -0.0001

Data Index: 20795 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2858. Min Act: -0.0001

Data Index: 1017664 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2766. Min Act: -0.0001

Data Index: 678502 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2477. Min Act: -0.0001

Data Index: 1331946 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2912. Min Act: -0.0001

Data Index: 251005 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2920. Min Act: -0.0001

Data Index: 1167722 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2790. Min Act: -0.0001

Data Index: 423081 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2886. Min Act: -0.0001

Data Index: 678509 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2558. Min Act: -0.0001

Data Index: 932118 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2577. Min Act: -0.0001

Data Index: 575541 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2315. Min Act: -0.0001

Data Index: 679437 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2632. Min Act: -0.0001

Data Index: 938138 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2566. Min Act: -0.0001

Data Index: 704497 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2627. Min Act: -0.0001

Data Index: 392865 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2111. Min Act: -0.0001

Data Index: 944013 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2328. Min Act: -0.0001

Data Index: 821241 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2680. Min Act: -0.0001

Data Index: 723193 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2657. Min Act: -0.0001

Data Index: 309039 (C4 (Web Text))

Max Activating Token Index: 665