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

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

Neuron 961 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9811. Min Act: -0.0000

Data Index: 576314 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1284969 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8661. Min Act: -0.0000

Data Index: 946799 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8236. Min Act: -0.0000

Data Index: 674125 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7759. Min Act: -0.0000

Data Index: 449138 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8381. Min Act: -0.0000

Data Index: 559244 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7692. Min Act: -0.0000

Data Index: 69915 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1163076 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8393. Min Act: -0.0000

Data Index: 515413 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.6236. Min Act: -0.0000

Data Index: 126952 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.6727. Min Act: -0.0000

Data Index: 47993 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.6607. Min Act: -0.0000

Data Index: 256882 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.6979. Min Act: -0.0000

Data Index: 775966 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.6925. Min Act: -0.0000

Data Index: 164200 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.6779. Min Act: -0.0000

Data Index: 688894 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8027. Min Act: -0.0000

Data Index: 746837 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1207516 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.7016. Min Act: -0.0000

Data Index: 924748 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.6396. Min Act: -0.0000

Data Index: 866985 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1170252 (C4 (Web Text))

Max Activating Token Index: 601