Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2596 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2412. Min Act: -0.0001

Data Index: 91287 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2413. Min Act: -0.0001

Data Index: 407382 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2554. Min Act: -0.0001

Data Index: 699987 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2734. Min Act: -0.0001

Data Index: 143738 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2169. Min Act: -0.0001

Data Index: 949243 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2248. Min Act: -0.0001

Data Index: 1066919 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2206. Min Act: -0.0001

Data Index: 1213265 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2219. Min Act: -0.0001

Data Index: 777281 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2156. Min Act: -0.0001

Data Index: 653880 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2245. Min Act: -0.0001

Data Index: 280536 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1987. Min Act: -0.0001

Data Index: 672678 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1962. Min Act: -0.0001

Data Index: 720626 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2187. Min Act: -0.0001

Data Index: 364709 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1038533 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1979. Min Act: -0.0001

Data Index: 701635 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1916. Min Act: -0.0001

Data Index: 35722 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1969. Min Act: -0.0001

Data Index: 438774 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2055. Min Act: -0.0001

Data Index: 368602 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1871. Min Act: -0.0001

Data Index: 933068 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1875. Min Act: -0.0001

Data Index: 949586 (C4 (Web Text))

Max Activating Token Index: 85