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

Dataset: The Pile

Neuron 1830 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1861164 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1632517 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1116498 (The Pile)

Max Activating Token Index: 163

Text #3

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7855. Min Act: -0.0000

Data Index: 869027 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7030. Min Act: -0.0000

Data Index: 210382 (The Pile)

Max Activating Token Index: 608

Text #5

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6584. Min Act: -0.0000

Data Index: 992910 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6679. Min Act: -0.0000

Data Index: 802562 (The Pile)

Max Activating Token Index: 170

Text #7

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1260606 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1782672 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6311. Min Act: -0.0000

Data Index: 553772 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1411890 (The Pile)

Max Activating Token Index: 77

Text #11

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1112817 (The Pile)

Max Activating Token Index: 703

Text #12

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5621. Min Act: -0.0000

Data Index: 459221 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5418. Min Act: -0.0000

Data Index: 50908 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1309749 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5182. Min Act: -0.0000

Data Index: 660373 (The Pile)

Max Activating Token Index: 124

Text #16

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1153029 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.4931. Min Act: -0.0000

Data Index: 661996 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.4438. Min Act: -0.0000

Data Index: 822027 (The Pile)

Max Activating Token Index: 917

Text #19

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1572310 (The Pile)

Max Activating Token Index: 471