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

Dataset: The Pile

Neuron 2141 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.9261. Min Act: -0.0000

Data Index: 108759 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1890767 (The Pile)

Max Activating Token Index: 684

Text #2

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8554. Min Act: -0.0000

Data Index: 709019 (The Pile)

Max Activating Token Index: 609

Text #3

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7262. Min Act: -0.0000

Data Index: 178114 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7011. Min Act: -0.0000

Data Index: 684403 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6771. Min Act: -0.0000

Data Index: 28783 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6445. Min Act: -0.0000

Data Index: 220759 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1056908 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6378. Min Act: -0.0000

Data Index: 679002 (The Pile)

Max Activating Token Index: 605

Text #9

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6328. Min Act: -0.0000

Data Index: 101641 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1444648 (The Pile)

Max Activating Token Index: 655

Text #11

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1091330 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5732. Min Act: -0.0000

Data Index: 965719 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5826. Min Act: -0.0000

Data Index: 661518 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6166. Min Act: -0.0000

Data Index: 798445 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1691251 (The Pile)

Max Activating Token Index: 131

Text #16

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1904746 (The Pile)

Max Activating Token Index: 74

Text #17

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1592991 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1613335 (The Pile)

Max Activating Token Index: 781

Text #19

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5485. Min Act: -0.0000

Data Index: 379200 (The Pile)

Max Activating Token Index: 275