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

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

Neuron 3627 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.9859. Min Act: -0.0000

Data Index: 1107459 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.7490. Min Act: -0.0000

Data Index: 1445849 (Python Code)

Max Activating Token Index: 817

Text #2

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.7524. Min Act: -0.0000

Data Index: 309136 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.5971. Min Act: -0.0000

Data Index: 953444 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.5088. Min Act: -0.0000

Data Index: 990792 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.4925. Min Act: -0.0000

Data Index: 1445967 (Python Code)

Max Activating Token Index: 499

Text #6

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.4021. Min Act: -0.0000

Data Index: 1579450 (Python Code)

Max Activating Token Index: 443

Text #7

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.4645. Min Act: -0.0000

Data Index: 1596389 (Python Code)

Max Activating Token Index: 158

Text #8

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.4219. Min Act: -0.0000

Data Index: 64286 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.4011. Min Act: -0.0000

Data Index: 1461627 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.4068. Min Act: -0.0000

Data Index: 1212858 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1383285 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.2908. Min Act: -0.0000

Data Index: 434324 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.2521. Min Act: -0.0000

Data Index: 1405998 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1372704 (Python Code)

Max Activating Token Index: 668

Text #15

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.3297. Min Act: -0.0000

Data Index: 669261 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.2365. Min Act: -0.0000

Data Index: 1159471 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.3070. Min Act: -0.0000

Data Index: 51488 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1094011 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 1.9859. Min Range: -1.9859

Max Act: 1.2714. Min Act: -0.0000

Data Index: 1980 (C4 (Web Text))

Max Activating Token Index: 988