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

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

Neuron 5753 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.9549. Min Act: -0.0000

Data Index: 746447 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.9478. Min Act: -0.0000

Data Index: 793467 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7727. Min Act: -0.0000

Data Index: 268719 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7650. Min Act: -0.0000

Data Index: 963952 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1063899 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1316044 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7600. Min Act: -0.0000

Data Index: 378239 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1222741 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6730. Min Act: -0.0000

Data Index: 568383 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6928. Min Act: -0.0000

Data Index: 352746 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1329929 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7100. Min Act: -0.0000

Data Index: 778405 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6417. Min Act: -0.0000

Data Index: 397998 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1245110 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7138. Min Act: -0.0000

Data Index: 964209 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6301. Min Act: -0.0000

Data Index: 317868 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1040029 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6559. Min Act: -0.0000

Data Index: 14105 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6290. Min Act: -0.0000

Data Index: 206834 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6324. Min Act: -0.0000

Data Index: 346885 (C4 (Web Text))

Max Activating Token Index: 908