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

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

Neuron 800 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0002

Data Index: 789648 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0002

Data Index: 581454 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1004445 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0463. Min Act: -0.0002

Data Index: 277743 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1036283 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1135471 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0365. Min Act: -0.0002

Data Index: 794484 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0354. Min Act: -0.0002

Data Index: 637387 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0353. Min Act: -0.0002

Data Index: 958916 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1027915 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0347. Min Act: -0.0002

Data Index: 735494 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1114884 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0342. Min Act: -0.0002

Data Index: 26288 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0341. Min Act: -0.0002

Data Index: 375747 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0334. Min Act: -0.0002

Data Index: 614292 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0330. Min Act: -0.0002

Data Index: 598926 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0329. Min Act: -0.0002

Data Index: 202186 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0329. Min Act: -0.0002

Data Index: 992869 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0328. Min Act: -0.0002

Data Index: 949667 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0324. Min Act: -0.0002

Data Index: 624598 (C4 (Web Text))

Max Activating Token Index: 322