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

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

Neuron 2708 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.3872. Min Act: -0.0000

Data Index: 172740 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.3358. Min Act: -0.0000

Data Index: 754479 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2947. Min Act: -0.0000

Data Index: 912580 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2800. Min Act: -0.0000

Data Index: 597225 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2655. Min Act: -0.0000

Data Index: 499298 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2742. Min Act: -0.0000

Data Index: 394961 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2518. Min Act: -0.0000

Data Index: 674689 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2939. Min Act: -0.0000

Data Index: 275559 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1294413 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2614. Min Act: -0.0000

Data Index: 519879 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2619. Min Act: -0.0000

Data Index: 528744 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2662. Min Act: -0.0000

Data Index: 959598 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2409. Min Act: -0.0000

Data Index: 782701 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1318034 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2519. Min Act: -0.0000

Data Index: 181369 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2381. Min Act: -0.0000

Data Index: 933617 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1237995 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2340. Min Act: -0.0000

Data Index: 825308 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2459. Min Act: -0.0000

Data Index: 300000 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.3872. Min Range: -0.3872

Max Act: 0.2303. Min Act: -0.0000

Data Index: 722308 (C4 (Web Text))

Max Activating Token Index: 118