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

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

Neuron 1955 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.8191. Min Act: 0.0000

Data Index: 804515 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.8819. Min Act: -0.0000

Data Index: 38890 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.1911. Min Act: -0.0000

Data Index: 1123012 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.0872. Min Act: -0.0000

Data Index: 1137583 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.1604. Min Act: -0.0000

Data Index: 515132 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.0901. Min Act: 0.0000

Data Index: 909133 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.2167. Min Act: -0.0000

Data Index: 1086399 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.2182. Min Act: -0.0000

Data Index: 1322362 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.0667. Min Act: -0.0000

Data Index: 786760 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.0196. Min Act: -0.0000

Data Index: 1316378 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.0171. Min Act: -0.0000

Data Index: 945836 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.8819. Min Range: -3.8819

Max Act: 2.9538. Min Act: -0.0000

Data Index: 815099 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.1977. Min Act: -0.0000

Data Index: 565583 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 3.8819. Min Range: -3.8819

Max Act: 2.7815. Min Act: -0.0000

Data Index: 165792 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 3.8819. Min Range: -3.8819

Max Act: 3.0455. Min Act: -0.0000

Data Index: 1352598 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.8819. Min Range: -3.8819

Max Act: 2.7980. Min Act: -0.0000

Data Index: 317132 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 3.8819. Min Range: -3.8819

Max Act: 1.8313. Min Act: -0.0000

Data Index: 823372 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 3.8819. Min Range: -3.8819

Max Act: 2.6794. Min Act: -0.0000

Data Index: 984434 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 3.8819. Min Range: -3.8819

Max Act: 2.6502. Min Act: -0.0000

Data Index: 1061382 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 3.8819. Min Range: -3.8819

Max Act: 2.6252. Min Act: -0.0000

Data Index: 197258 (C4 (Web Text))

Max Activating Token Index: 26