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

Dataset: The Pile

Neuron 3473 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: 1.7563. Min Range: -1.7563

Max Act: 1.7563. Min Act: -0.0000

Data Index: 339928 (The Pile)

Max Activating Token Index: 925

Text #1

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.7433. Min Act: -0.0000

Data Index: 1410723 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.6353. Min Act: -0.0000

Data Index: 1784044 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.4894. Min Act: -0.0000

Data Index: 1636501 (The Pile)

Max Activating Token Index: 537

Text #4

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.4221. Min Act: -0.0000

Data Index: 1877863 (The Pile)

Max Activating Token Index: 129

Text #5

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.5743. Min Act: -0.0000

Data Index: 728668 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.4715. Min Act: -0.0000

Data Index: 227092 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.4440. Min Act: -0.0000

Data Index: 850913 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.4156. Min Act: -0.0000

Data Index: 1072976 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3178. Min Act: -0.0000

Data Index: 782164 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1606952 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3378. Min Act: -0.0000

Data Index: 199107 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1906273 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.2839. Min Act: -0.0000

Data Index: 527991 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1504697 (The Pile)

Max Activating Token Index: 645

Text #15

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3152. Min Act: -0.0000

Data Index: 538702 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1432792 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3131. Min Act: -0.0000

Data Index: 1773574 (The Pile)

Max Activating Token Index: 116

Text #18

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.2326. Min Act: -0.0000

Data Index: 637928 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.2976. Min Act: -0.0000

Data Index: 1065559 (The Pile)

Max Activating Token Index: 755