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

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

Neuron 1216 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0001

Data Index: 639970 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2223. Min Act: -0.0000

Data Index: 344283 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2294. Min Act: -0.0000

Data Index: 864088 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2230. Min Act: -0.0001

Data Index: 182894 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1068143 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2292. Min Act: -0.0000

Data Index: 631392 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2103. Min Act: -0.0001

Data Index: 400336 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2090. Min Act: -0.0001

Data Index: 307102 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1861. Min Act: -0.0000

Data Index: 913872 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1916. Min Act: -0.0000

Data Index: 779328 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1196722 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1924. Min Act: -0.0000

Data Index: 929861 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1798. Min Act: -0.0000

Data Index: 457626 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1289807 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1981. Min Act: -0.0001

Data Index: 926366 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1703. Min Act: -0.0000

Data Index: 328192 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1772. Min Act: -0.0001

Data Index: 532221 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1020781 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1165410 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1773. Min Act: -0.0000

Data Index: 942912 (C4 (Web Text))

Max Activating Token Index: 465