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

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

Neuron 2520 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: 1.4822. Min Range: -1.4822

Max Act: 1.4822. Min Act: -0.0000

Data Index: 788195 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.4804. Min Act: -0.0000

Data Index: 1177815 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.3629. Min Act: -0.0000

Data Index: 612588 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.4005. Min Act: -0.0000

Data Index: 255981 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.2441. Min Act: -0.0000

Data Index: 651642 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1175506 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.2933. Min Act: -0.0000

Data Index: 1357007 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.2843. Min Act: -0.0000

Data Index: 257194 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.2548. Min Act: -0.0000

Data Index: 237259 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.2472. Min Act: -0.0000

Data Index: 47396 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1205. Min Act: -0.0000

Data Index: 556819 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1224. Min Act: -0.0000

Data Index: 394070 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1147219 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.0471. Min Act: -0.0000

Data Index: 833475 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1084. Min Act: -0.0000

Data Index: 36044 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1344799 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1012. Min Act: -0.0000

Data Index: 1091899 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.0698. Min Act: -0.0000

Data Index: 936376 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.0123. Min Act: -0.0000

Data Index: 455881 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.0406. Min Act: -0.0000

Data Index: 899459 (C4 (Web Text))

Max Activating Token Index: 744