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

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

Neuron 2622 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 13.8619. Min Range: -13.8619

Max Act: 13.8619. Min Act: -0.0000

Data Index: 1258106 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 13.8619. Min Range: -13.8619

Max Act: 12.6942. Min Act: -0.0001

Data Index: 1259692 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 13.8619. Min Range: -13.8619

Max Act: 10.6313. Min Act: -0.0000

Data Index: 1206583 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 13.8619. Min Range: -13.8619

Max Act: 11.6548. Min Act: -0.0000

Data Index: 870519 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 13.8619. Min Range: -13.8619

Max Act: 9.9770. Min Act: -0.0001

Data Index: 41078 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 13.8619. Min Range: -13.8619

Max Act: 6.5274. Min Act: -0.0001

Data Index: 653994 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 13.8619. Min Range: -13.8619

Max Act: 4.9122. Min Act: -0.0000

Data Index: 866530 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 13.8619. Min Range: -13.8619

Max Act: 3.1771. Min Act: -0.0001

Data Index: 1314783 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 13.8619. Min Range: -13.8619

Max Act: 1.5906. Min Act: -0.0000

Data Index: 1117742 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 13.8619. Min Range: -13.8619

Max Act: 2.1881. Min Act: -0.0000

Data Index: 647961 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 13.8619. Min Range: -13.8619

Max Act: 1.8121. Min Act: -0.0000

Data Index: 127540 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 13.8619. Min Range: -13.8619

Max Act: 1.9288. Min Act: -0.0000

Data Index: 739117 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 13.8619. Min Range: -13.8619

Max Act: 1.0434. Min Act: -0.0001

Data Index: 379263 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 13.8619. Min Range: -13.8619

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1029442 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 13.8619. Min Range: -13.8619

Max Act: 0.9578. Min Act: -0.0001

Data Index: 1038669 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 13.8619. Min Range: -13.8619

Max Act: 0.4418. Min Act: -0.0001

Data Index: 1027170 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 13.8619. Min Range: -13.8619

Max Act: 1.5000. Min Act: -0.0000

Data Index: 319458 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 13.8619. Min Range: -13.8619

Max Act: 0.2899. Min Act: -0.0000

Data Index: 139092 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 13.8619. Min Range: -13.8619

Max Act: 0.3216. Min Act: -0.0001

Data Index: 708723 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 13.8619. Min Range: -13.8619

Max Act: 0.2053. Min Act: -0.0000

Data Index: 544975 (C4 (Web Text))

Max Activating Token Index: 386