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

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

Neuron 3371 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2886. Min Range: -1.2886

Max Act: 1.2886. Min Act: -0.0000

Data Index: 799155 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 1.2886. Min Range: -1.2886

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1171355 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 1.2886. Min Range: -1.2886

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1232764 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1185878 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.9306. Min Act: -0.0000

Data Index: 232628 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1330771 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.8674. Min Act: -0.0000

Data Index: 27371 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.8873. Min Act: -0.0000

Data Index: 949474 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.8826. Min Act: -0.0000

Data Index: 505344 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.8414. Min Act: -0.0000

Data Index: 823550 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1338192 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1158361 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1355520 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.7956. Min Act: -0.0000

Data Index: 240232 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.9097. Min Act: -0.0000

Data Index: 301262 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1122274 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.7742. Min Act: -0.0000

Data Index: 295705 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.7477. Min Act: -0.0000

Data Index: 363303 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1021902 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.2886. Min Range: -1.2886

Max Act: 0.7293. Min Act: -0.0000

Data Index: 845366 (C4 (Web Text))

Max Activating Token Index: 64