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

Dataset: The Pile

Neuron 707 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: 1.2854. Min Range: -1.2854

Max Act: 1.2725. Min Act: -0.0000

Data Index: 383253 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1519090 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2484. Min Act: -0.0000

Data Index: 947002 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2516. Min Act: -0.0000

Data Index: 1614438 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2817. Min Act: -0.0000

Data Index: 1726315 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2091. Min Act: -0.0000

Data Index: 676828 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2244. Min Act: -0.0000

Data Index: 1640971 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2730. Min Act: -0.0000

Data Index: 285542 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2407. Min Act: -0.0000

Data Index: 931253 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2854. Min Act: -0.0000

Data Index: 163772 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2552. Min Act: -0.0000

Data Index: 1647888 (The Pile)

Max Activating Token Index: 126

Text #11

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2416. Min Act: -0.0000

Data Index: 843860 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2292. Min Act: -0.0000

Data Index: 1198635 (The Pile)

Max Activating Token Index: 354

Text #13

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1506902 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2183. Min Act: -0.0000

Data Index: 668664 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1384154 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2068. Min Act: -0.0000

Data Index: 35368 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1082787 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1151728 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.1655. Min Act: -0.0000

Data Index: 1645812 (The Pile)

Max Activating Token Index: 203