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

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

Neuron 5005 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: 2.7981. Min Range: -2.7981

Max Act: 2.7981. Min Act: -0.0000

Data Index: 147131 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.7733. Min Act: -0.0000

Data Index: 262540 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.5837. Min Act: -0.0000

Data Index: 974929 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.4121. Min Act: -0.0000

Data Index: 1318204 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.3759. Min Act: -0.0000

Data Index: 102955 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.3323. Min Act: -0.0000

Data Index: 1065355 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.2477. Min Act: -0.0000

Data Index: 404563 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.2941. Min Act: -0.0000

Data Index: 363004 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.1169. Min Act: -0.0000

Data Index: 1286138 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.2124. Min Act: -0.0000

Data Index: 791418 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.0682. Min Act: -0.0000

Data Index: 819358 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 2.7981. Min Range: -2.7981

Max Act: 1.9966. Min Act: -0.0000

Data Index: 335436 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.1949. Min Act: -0.0000

Data Index: 487744 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 2.7981. Min Range: -2.7981

Max Act: 1.9540. Min Act: -0.0000

Data Index: 1345311 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.1672. Min Act: -0.0000

Data Index: 552640 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.0590. Min Act: -0.0000

Data Index: 776831 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 2.7981. Min Range: -2.7981

Max Act: 1.9230. Min Act: -0.0000

Data Index: 1062664 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 2.7981. Min Range: -2.7981

Max Act: 1.9245. Min Act: -0.0000

Data Index: 818285 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 2.7981. Min Range: -2.7981

Max Act: 2.0205. Min Act: -0.0000

Data Index: 1204696 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 2.7981. Min Range: -2.7981

Max Act: 1.9027. Min Act: -0.0000

Data Index: 277005 (C4 (Web Text))

Max Activating Token Index: 54