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

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

Neuron 3717 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2267. Min Range: -2.2267

Max Act: 2.2267. Min Act: -0.0000

Data Index: 918970 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 2.2267. Min Range: -2.2267

Max Act: 2.1017. Min Act: -0.0000

Data Index: 865203 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 2.2267. Min Range: -2.2267

Max Act: 2.1349. Min Act: -0.0000

Data Index: 452696 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 2.2267. Min Range: -2.2267

Max Act: 2.0324. Min Act: -0.0000

Data Index: 31750 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.9693. Min Act: -0.0000

Data Index: 109694 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.8696. Min Act: -0.0000

Data Index: 721327 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.9176. Min Act: -0.0000

Data Index: 1345078 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 2.2267. Min Range: -2.2267

Max Act: 2.0084. Min Act: -0.0000

Data Index: 969978 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.8715. Min Act: -0.0000

Data Index: 381567 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.9439. Min Act: -0.0000

Data Index: 452352 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.7881. Min Act: -0.0000

Data Index: 1069727 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.9466. Min Act: -0.0000

Data Index: 1318062 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.9390. Min Act: -0.0000

Data Index: 346177 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.9362. Min Act: -0.0000

Data Index: 569585 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.9844. Min Act: -0.0000

Data Index: 567860 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.8600. Min Act: -0.0000

Data Index: 591124 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.8033. Min Act: -0.0000

Data Index: 1132529 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.8486. Min Act: -0.0000

Data Index: 1026349 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.8856. Min Act: -0.0000

Data Index: 418215 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.7690. Min Act: -0.0000

Data Index: 1177779 (C4 (Web Text))

Max Activating Token Index: 377