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

Dataset: The Pile

Neuron 3210 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.5097. Min Act: -0.0000

Data Index: 1782418 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.6894. Min Act: -0.0000

Data Index: 1085077 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.4043. Min Act: -0.0000

Data Index: 1940924 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.3256. Min Act: -0.0000

Data Index: 1047143 (The Pile)

Max Activating Token Index: 741

Text #4

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.1576. Min Act: -0.0000

Data Index: 1556357 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.2450. Min Act: -0.0000

Data Index: 800229 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 3.6894. Min Range: -3.6894

Max Act: 2.9838. Min Act: -0.0000

Data Index: 1620627 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.2315. Min Act: -0.0000

Data Index: 588167 (The Pile)

Max Activating Token Index: 390

Text #8

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.2457. Min Act: -0.0000

Data Index: 735330 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.0010. Min Act: -0.0000

Data Index: 315258 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 3.6894. Min Range: -3.6894

Max Act: 2.9972. Min Act: -0.0000

Data Index: 1647855 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.1338. Min Act: -0.0000

Data Index: 1134909 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.1079. Min Act: 0.0000

Data Index: 184126 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.1219. Min Act: -0.0000

Data Index: 778111 (The Pile)

Max Activating Token Index: 735

Text #14

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.0755. Min Act: -0.0000

Data Index: 647330 (The Pile)

Max Activating Token Index: 742

Text #15

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.0723. Min Act: -0.0000

Data Index: 1948977 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.0525. Min Act: -0.0000

Data Index: 1177586 (The Pile)

Max Activating Token Index: 771

Text #17

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.0588. Min Act: -0.0000

Data Index: 906829 (The Pile)

Max Activating Token Index: 769

Text #18

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.3566. Min Act: -0.0000

Data Index: 441945 (The Pile)

Max Activating Token Index: 641

Text #19

Max Range: 3.6894. Min Range: -3.6894

Max Act: 3.0445. Min Act: -0.0000

Data Index: 826754 (The Pile)

Max Activating Token Index: 114