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

Dataset: The Pile

Neuron 4147 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.7235. Min Act: -0.0000

Data Index: 705653 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1811532 (The Pile)

Max Activating Token Index: 685

Text #2

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6213. Min Act: -0.0000

Data Index: 623849 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6044. Min Act: -0.0000

Data Index: 795286 (The Pile)

Max Activating Token Index: 943

Text #4

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1364502 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5882. Min Act: -0.0000

Data Index: 1342235 (The Pile)

Max Activating Token Index: 922

Text #6

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1430698 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5662. Min Act: -0.0000

Data Index: 429512 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6187. Min Act: -0.0000

Data Index: 587736 (The Pile)

Max Activating Token Index: 179

Text #9

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1497805 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1624250 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.4960. Min Act: -0.0000

Data Index: 185850 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1673644 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5614. Min Act: -0.0000

Data Index: 945967 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1100213 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5520. Min Act: -0.0000

Data Index: 692830 (The Pile)

Max Activating Token Index: 200

Text #16

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1273798 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5342. Min Act: -0.0000

Data Index: 368888 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5372. Min Act: -0.0000

Data Index: 361601 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5326. Min Act: -0.0000

Data Index: 652226 (The Pile)

Max Activating Token Index: 152