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

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

Neuron 1722 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: 1.2242. Min Range: -1.2242

Max Act: 1.2242. Min Act: -0.0000

Data Index: 68074 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.0926. Min Act: -0.0000

Data Index: 832843 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1196551 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9282. Min Act: -0.0000

Data Index: 527821 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1033661 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1317881 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1057708 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7427. Min Act: -0.0000

Data Index: 90407 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7885. Min Act: -0.0000

Data Index: 559025 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7397. Min Act: -0.0000

Data Index: 189669 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7624. Min Act: -0.0000

Data Index: 173010 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8066. Min Act: -0.0000

Data Index: 627091 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7525. Min Act: -0.0000

Data Index: 755594 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7030. Min Act: -0.0000

Data Index: 583879 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7712. Min Act: -0.0000

Data Index: 532143 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7216. Min Act: -0.0000

Data Index: 621474 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7203. Min Act: -0.0000

Data Index: 421443 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1148603 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7338. Min Act: -0.0000

Data Index: 723946 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7529. Min Act: -0.0000

Data Index: 220510 (C4 (Web Text))

Max Activating Token Index: 102