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

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

Neuron 3766 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3605. Min Range: -4.3605

Max Act: 4.3605. Min Act: -0.0001

Data Index: 97970 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 4.3605. Min Range: -4.3605

Max Act: 4.2011. Min Act: -0.0001

Data Index: 822500 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 4.3605. Min Range: -4.3605

Max Act: 4.3421. Min Act: -0.0001

Data Index: 156062 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.9821. Min Act: -0.0001

Data Index: 407185 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.8527. Min Act: -0.0001

Data Index: 46580 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.7496. Min Act: -0.0001

Data Index: 37172 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.7439. Min Act: -0.0001

Data Index: 1286631 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.7057. Min Act: -0.0001

Data Index: 156656 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.7151. Min Act: -0.0001

Data Index: 965318 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.6941. Min Act: -0.0001

Data Index: 434148 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.5812. Min Act: -0.0001

Data Index: 505822 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.5327. Min Act: -0.0001

Data Index: 1095710 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.4649. Min Act: -0.0001

Data Index: 577955 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.4556. Min Act: -0.0001

Data Index: 1216641 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.4337. Min Act: -0.0001

Data Index: 734352 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.4410. Min Act: -0.0001

Data Index: 590086 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.2895. Min Act: -0.0001

Data Index: 1077175 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.4094. Min Act: -0.0001

Data Index: 198562 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.4019. Min Act: -0.0001

Data Index: 1326902 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 4.3605. Min Range: -4.3605

Max Act: 3.3926. Min Act: -0.0001

Data Index: 21020 (C4 (Web Text))

Max Activating Token Index: 38