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

Dataset: The Pile

Neuron 3034 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1121009 (The Pile)

Max Activating Token Index: 204

Text #1

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8664. Min Act: -0.0000

Data Index: 526832 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8338. Min Act: -0.0000

Data Index: 68908 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1465697 (The Pile)

Max Activating Token Index: 722

Text #4

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1528294 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6501. Min Act: -0.0000

Data Index: 401840 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1458104 (The Pile)

Max Activating Token Index: 797

Text #7

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6151. Min Act: -0.0000

Data Index: 916330 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6308. Min Act: -0.0000

Data Index: 425054 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1605214 (The Pile)

Max Activating Token Index: 642

Text #10

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6065. Min Act: -0.0000

Data Index: 26172 (The Pile)

Max Activating Token Index: 791

Text #11

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1228716 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.5800. Min Act: -0.0000

Data Index: 1554164 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.5807. Min Act: -0.0000

Data Index: 319569 (The Pile)

Max Activating Token Index: 436

Text #14

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1871663 (The Pile)

Max Activating Token Index: 400

Text #15

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1543008 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.5013. Min Act: -0.0000

Data Index: 601867 (The Pile)

Max Activating Token Index: 613

Text #17

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6180. Min Act: -0.0000

Data Index: 341733 (The Pile)

Max Activating Token Index: 689

Text #18

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.5269. Min Act: -0.0000

Data Index: 76009 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.5303. Min Act: -0.0000

Data Index: 640088 (The Pile)

Max Activating Token Index: 607