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

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

Neuron 4461 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.7634. Min Act: -0.0000

Data Index: 769863 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.7609. Min Act: -0.0000

Data Index: 84842 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.7121. Min Act: -0.0000

Data Index: 694070 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6459. Min Act: -0.0000

Data Index: 58473 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6260. Min Act: -0.0000

Data Index: 400714 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6396. Min Act: -0.0000

Data Index: 560651 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1293069 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5239. Min Act: -0.0000

Data Index: 243799 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6110. Min Act: -0.0000

Data Index: 964810 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6049. Min Act: -0.0000

Data Index: 606468 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1111649 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6191. Min Act: -0.0000

Data Index: 771686 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1164856 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1213499 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5185. Min Act: -0.0000

Data Index: 408655 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5311. Min Act: -0.0000

Data Index: 422970 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5040. Min Act: -0.0000

Data Index: 865772 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5139. Min Act: -0.0000

Data Index: 845436 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.4606. Min Act: -0.0000

Data Index: 466559 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.4897. Min Act: -0.0000

Data Index: 407275 (C4 (Web Text))

Max Activating Token Index: 606