Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5037 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3825. Min Range: -3.3825

Max Act: 3.3825. Min Act: -0.0000

Data Index: 506553 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 3.3825. Min Range: -3.3825

Max Act: 3.1754. Min Act: -0.0000

Data Index: 1102979 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 3.3825. Min Range: -3.3825

Max Act: 3.2212. Min Act: -0.0000

Data Index: 638429 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 3.3825. Min Range: -3.3825

Max Act: 3.2200. Min Act: -0.0000

Data Index: 766453 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.9925. Min Act: -0.0000

Data Index: 875272 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 3.3825. Min Range: -3.3825

Max Act: 3.0405. Min Act: -0.0000

Data Index: 500524 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.8559. Min Act: -0.0000

Data Index: 843136 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.9763. Min Act: -0.0000

Data Index: 60472 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.9459. Min Act: -0.0000

Data Index: 1253157 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.7806. Min Act: -0.0000

Data Index: 415842 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.9265. Min Act: -0.0000

Data Index: 312841 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.9066. Min Act: -0.0000

Data Index: 941615 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.5981. Min Act: -0.0000

Data Index: 781989 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.7147. Min Act: -0.0000

Data Index: 834645 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.9934. Min Act: -0.0000

Data Index: 475324 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.7028. Min Act: -0.0000

Data Index: 6525 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.3067. Min Act: -0.0000

Data Index: 383703 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.7110. Min Act: -0.0000

Data Index: 832252 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.6970. Min Act: -0.0000

Data Index: 560825 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 3.3825. Min Range: -3.3825

Max Act: 2.5433. Min Act: -0.0000

Data Index: 413401 (C4 (Web Text))

Max Activating Token Index: 649