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

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

Neuron 4321 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7659. Min Act: -0.0001

Data Index: 159735 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7116. Min Act: -0.0001

Data Index: 774992 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6765. Min Act: -0.0001

Data Index: 401920 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7977. Min Act: -0.0001

Data Index: 286711 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7074. Min Act: -0.0001

Data Index: 751364 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7843. Min Act: -0.0001

Data Index: 654521 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7573. Min Act: -0.0001

Data Index: 312187 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6711. Min Act: -0.0001

Data Index: 1325339 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7486. Min Act: -0.0001

Data Index: 1145226 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7698. Min Act: -0.0001

Data Index: 753407 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7331. Min Act: -0.0001

Data Index: 907376 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7551. Min Act: -0.0001

Data Index: 228949 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7758. Min Act: -0.0001

Data Index: 155024 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6665. Min Act: -0.0001

Data Index: 422844 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6756. Min Act: -0.0001

Data Index: 1345697 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6563. Min Act: -0.0001

Data Index: 992979 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7084. Min Act: -0.0001

Data Index: 542499 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6828. Min Act: -0.0001

Data Index: 717210 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7346. Min Act: -0.0001

Data Index: 1351229 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7018. Min Act: -0.0001

Data Index: 480506 (C4 (Web Text))

Max Activating Token Index: 7