Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 689 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.9213. Min Act: -0.0001

Data Index: 107111 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.8726. Min Act: -0.0001

Data Index: 1235443 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.8025. Min Act: -0.0001

Data Index: 423278 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.6471. Min Act: -0.0000

Data Index: 833580 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.5935. Min Act: -0.0001

Data Index: 1151150 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.4481. Min Act: -0.0000

Data Index: 333362 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.5323. Min Act: -0.0000

Data Index: 680214 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.5667. Min Act: -0.0001

Data Index: 204803 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.4729. Min Act: -0.0001

Data Index: 334503 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.3813. Min Act: -0.0001

Data Index: 1304263 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.4676. Min Act: -0.0000

Data Index: 588659 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.5277. Min Act: -0.0001

Data Index: 550343 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.3548. Min Act: -0.0001

Data Index: 378756 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.4296. Min Act: -0.0000

Data Index: 614926 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.5081. Min Act: -0.0001

Data Index: 1526628 (Python Code)

Max Activating Token Index: 917

Text #15

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.4968. Min Act: -0.0001

Data Index: 340075 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.3340. Min Act: -0.0000

Data Index: 862104 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.3853. Min Act: -0.0001

Data Index: 1000392 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.3084. Min Act: -0.0001

Data Index: 1042979 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 1.9213. Min Range: -1.9213

Max Act: 1.3710. Min Act: -0.0001

Data Index: 295926 (C4 (Web Text))

Max Activating Token Index: 644