Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 440 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.9741. Min Act: -0.0000

Data Index: 1420995 (The Pile)

Max Activating Token Index: 947

Text #1

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8744. Min Act: -0.0000

Data Index: 669211 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1637985 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1210101 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1469180 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7525. Min Act: -0.0000

Data Index: 936610 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1011136 (The Pile)

Max Activating Token Index: 177

Text #7

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1008970 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1536292 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6812. Min Act: -0.0000

Data Index: 920053 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8168. Min Act: -0.0000

Data Index: 778899 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7114. Min Act: -0.0000

Data Index: 127973 (The Pile)

Max Activating Token Index: 166

Text #12

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1755422 (The Pile)

Max Activating Token Index: 125

Text #13

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7339. Min Act: -0.0000

Data Index: 367676 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7045. Min Act: -0.0000

Data Index: 1453668 (The Pile)

Max Activating Token Index: 304

Text #15

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7745. Min Act: -0.0000

Data Index: 886175 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1556901 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1696826 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1608181 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1071049 (The Pile)

Max Activating Token Index: 260