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

Dataset: The Pile

Neuron 4862 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1342484 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1774273 (The Pile)

Max Activating Token Index: 1005

Text #2

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1130682 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5727. Min Act: -0.0000

Data Index: 951528 (The Pile)

Max Activating Token Index: 861

Text #4

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1472656 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6192. Min Act: -0.0001

Data Index: 76280 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5965. Min Act: -0.0000

Data Index: 503528 (The Pile)

Max Activating Token Index: 967

Text #7

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6211. Min Act: -0.0000

Data Index: 549893 (The Pile)

Max Activating Token Index: 554

Text #8

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1135135 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5822. Min Act: -0.0000

Data Index: 37825 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1516980 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1649143 (The Pile)

Max Activating Token Index: 416

Text #12

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.6058. Min Act: -0.0000

Data Index: 680442 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5790. Min Act: -0.0001

Data Index: 552975 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1600564 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1236674 (The Pile)

Max Activating Token Index: 194

Text #16

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5686. Min Act: -0.0000

Data Index: 570654 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5674. Min Act: -0.0000

Data Index: 281496 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1271364 (The Pile)

Max Activating Token Index: 779

Text #19

Max Range: 0.7360. Min Range: -0.7360

Max Act: 0.5661. Min Act: -0.0000

Data Index: 63466 (The Pile)

Max Activating Token Index: 535