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

Dataset: The Pile

Neuron 1400 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.9479. Min Act: -0.0000

Data Index: 1958881 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1905780 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7177. Min Act: -0.0000

Data Index: 1236961 (The Pile)

Max Activating Token Index: 289

Text #3

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1115882 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7114. Min Act: -0.0000

Data Index: 412912 (The Pile)

Max Activating Token Index: 91

Text #5

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7524. Min Act: -0.0000

Data Index: 971884 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7172. Min Act: -0.0000

Data Index: 283104 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1833156 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6975. Min Act: -0.0000

Data Index: 763287 (The Pile)

Max Activating Token Index: 235

Text #9

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1985317 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1214791 (The Pile)

Max Activating Token Index: 886

Text #11

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1731453 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1213068 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5689. Min Act: -0.0000

Data Index: 528455 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1762219 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1128059 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1321373 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5723. Min Act: -0.0000

Data Index: 82914 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1545136 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6176. Min Act: -0.0000

Data Index: 729408 (The Pile)

Max Activating Token Index: 943