Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4018 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.7907. Min Act: -0.0001

Data Index: 721671 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.7734. Min Act: -0.0001

Data Index: 1023886 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.7308. Min Act: -0.0001

Data Index: 1035498 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.7597. Min Act: -0.0001

Data Index: 1153214 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.7449. Min Act: -0.0001

Data Index: 101499 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.7203. Min Act: -0.0001

Data Index: 942893 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6883. Min Act: -0.0001

Data Index: 347789 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6878. Min Act: -0.0000

Data Index: 653825 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6693. Min Act: -0.0001

Data Index: 754471 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6799. Min Act: -0.0000

Data Index: 176733 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.7099. Min Act: -0.0001

Data Index: 763364 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6902. Min Act: -0.0000

Data Index: 464976 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6627. Min Act: -0.0001

Data Index: 293277 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6757. Min Act: -0.0000

Data Index: 874987 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6580. Min Act: -0.0001

Data Index: 401699 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6379. Min Act: -0.0001

Data Index: 270886 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6380. Min Act: -0.0001

Data Index: 1113647 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6593. Min Act: -0.0001

Data Index: 989282 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6190. Min Act: -0.0001

Data Index: 498210 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.7907. Min Range: -0.7907

Max Act: 0.6525. Min Act: -0.0001

Data Index: 363773 (C4 (Web Text))

Max Activating Token Index: 1000