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

Dataset: The Pile

Neuron 3471 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.8332. Min Act: -0.0000

Data Index: 388190 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.8154. Min Act: -0.0000

Data Index: 703588 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1664297 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1074030 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6003. Min Act: -0.0000

Data Index: 665354 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1699406 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5756. Min Act: -0.0000

Data Index: 644968 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5226. Min Act: -0.0000

Data Index: 906884 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5620. Min Act: -0.0000

Data Index: 956134 (The Pile)

Max Activating Token Index: 704

Text #9

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1032640 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4998. Min Act: -0.0000

Data Index: 213629 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1769653 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4821. Min Act: -0.0000

Data Index: 924558 (The Pile)

Max Activating Token Index: 720

Text #13

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1115879 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4937. Min Act: -0.0000

Data Index: 351046 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1431364 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5238. Min Act: -0.0000

Data Index: 870988 (The Pile)

Max Activating Token Index: 75

Text #17

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1651817 (The Pile)

Max Activating Token Index: 378

Text #18

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1626891 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1497074 (The Pile)

Max Activating Token Index: 260