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

Dataset: The Pile

Neuron 3235 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4738. Min Range: -1.4738

Max Act: 1.4738. Min Act: -0.0000

Data Index: 1260767 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 1.4738. Min Range: -1.4738

Max Act: 1.0710. Min Act: -0.0000

Data Index: 378675 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 1.4738. Min Range: -1.4738

Max Act: 1.0229. Min Act: -0.0000

Data Index: 384136 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 1.4738. Min Range: -1.4738

Max Act: 1.0192. Min Act: -0.0000

Data Index: 1836823 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1988086 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1955881 (The Pile)

Max Activating Token Index: 725

Text #6

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8596. Min Act: -0.0000

Data Index: 363650 (The Pile)

Max Activating Token Index: 713

Text #7

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1225930 (The Pile)

Max Activating Token Index: 790

Text #8

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1951502 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1156743 (The Pile)

Max Activating Token Index: 189

Text #10

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1266336 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1056612 (The Pile)

Max Activating Token Index: 282

Text #12

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.7730. Min Act: -0.0000

Data Index: 745582 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1494816 (The Pile)

Max Activating Token Index: 871

Text #14

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.7541. Min Act: -0.0000

Data Index: 27209 (The Pile)

Max Activating Token Index: 887

Text #15

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.7561. Min Act: -0.0000

Data Index: 94010 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.8108. Min Act: -0.0000

Data Index: 92619 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.7320. Min Act: -0.0000

Data Index: 151424 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1090958 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 1.4738. Min Range: -1.4738

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1521502 (The Pile)

Max Activating Token Index: 547