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

Dataset: The Pile

Neuron 1831 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: 3.2975. Min Range: -3.2975

Max Act: 3.2975. Min Act: -0.0000

Data Index: 1797428 (The Pile)

Max Activating Token Index: 4

Text #1

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.5615. Min Act: -0.0000

Data Index: 808231 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.0453. Min Act: -0.0000

Data Index: 1865866 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.0723. Min Act: -0.0000

Data Index: 44911 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.6682. Min Act: -0.0000

Data Index: 1920133 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.6973. Min Act: -0.0000

Data Index: 29871 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.6670. Min Act: -0.0000

Data Index: 1117579 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.4812. Min Act: -0.0000

Data Index: 925539 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.3583. Min Act: -0.0000

Data Index: 1384934 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.7041. Min Act: -0.0000

Data Index: 1621383 (The Pile)

Max Activating Token Index: 245

Text #10

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.6037. Min Act: -0.0000

Data Index: 914808 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.3657. Min Act: -0.0000

Data Index: 1714989 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.1035. Min Act: -0.0000

Data Index: 809484 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.0508. Min Act: -0.0000

Data Index: 437420 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.1016. Min Act: -0.0000

Data Index: 165439 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 3.2975. Min Range: -3.2975

Max Act: 1.8902. Min Act: -0.0000

Data Index: 790441 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 3.2975. Min Range: -3.2975

Max Act: 2.1600. Min Act: -0.0000

Data Index: 773803 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 3.2975. Min Range: -3.2975

Max Act: 1.6568. Min Act: -0.0000

Data Index: 296952 (The Pile)

Max Activating Token Index: 964

Text #18

Max Range: 3.2975. Min Range: -3.2975

Max Act: 1.9044. Min Act: -0.0000

Data Index: 1041625 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 3.2975. Min Range: -3.2975

Max Act: 1.7203. Min Act: -0.0000

Data Index: 793525 (The Pile)

Max Activating Token Index: 1015