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

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

Neuron 3995 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0404. Min Range: -7.0404

Max Act: 7.0404. Min Act: -0.0001

Data Index: 266267 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 7.0404. Min Range: -7.0404

Max Act: 6.9903. Min Act: -0.0000

Data Index: 714358 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 7.0404. Min Range: -7.0404

Max Act: 6.5184. Min Act: -0.0000

Data Index: 1038110 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 7.0404. Min Range: -7.0404

Max Act: 6.8625. Min Act: -0.0001

Data Index: 979297 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 7.0404. Min Range: -7.0404

Max Act: 6.3019. Min Act: -0.0000

Data Index: 814924 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 7.0404. Min Range: -7.0404

Max Act: 6.1735. Min Act: -0.0000

Data Index: 434987 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 7.0404. Min Range: -7.0404

Max Act: 6.2817. Min Act: -0.0000

Data Index: 660045 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 7.0404. Min Range: -7.0404

Max Act: 6.2596. Min Act: -0.0000

Data Index: 1175653 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 7.0404. Min Range: -7.0404

Max Act: 5.8247. Min Act: -0.0000

Data Index: 383147 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 7.0404. Min Range: -7.0404

Max Act: 5.9372. Min Act: -0.0001

Data Index: 225355 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 7.0404. Min Range: -7.0404

Max Act: 5.9179. Min Act: -0.0000

Data Index: 1003413 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 7.0404. Min Range: -7.0404

Max Act: 5.6990. Min Act: -0.0000

Data Index: 1193241 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 7.0404. Min Range: -7.0404

Max Act: 5.9766. Min Act: -0.0000

Data Index: 1078958 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 7.0404. Min Range: -7.0404

Max Act: 5.7815. Min Act: -0.0000

Data Index: 851911 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 7.0404. Min Range: -7.0404

Max Act: 6.1086. Min Act: -0.0000

Data Index: 1127201 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 7.0404. Min Range: -7.0404

Max Act: 5.7370. Min Act: -0.0000

Data Index: 1213105 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 7.0404. Min Range: -7.0404

Max Act: 6.0650. Min Act: -0.0000

Data Index: 446230 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 7.0404. Min Range: -7.0404

Max Act: 5.6841. Min Act: -0.0000

Data Index: 481338 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 7.0404. Min Range: -7.0404

Max Act: 5.4831. Min Act: -0.0001

Data Index: 771520 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 7.0404. Min Range: -7.0404

Max Act: 5.6542. Min Act: -0.0000

Data Index: 1018383 (C4 (Web Text))

Max Activating Token Index: 732