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

Dataset: The Pile

Neuron 1024 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.3092. Min Act: -0.0000

Data Index: 964624 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9617. Min Act: -0.0000

Data Index: 563285 (The Pile)

Max Activating Token Index: 306

Text #2

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9322. Min Act: 0.0000

Data Index: 1698209 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9255. Min Act: -0.0000

Data Index: 843946 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1019219 (The Pile)

Max Activating Token Index: 490

Text #5

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1289923 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9129. Min Act: -0.0000

Data Index: 724767 (The Pile)

Max Activating Token Index: 862

Text #7

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1357705 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8482. Min Act: -0.0000

Data Index: 142304 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8020. Min Act: -0.0000

Data Index: 858542 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1639798 (The Pile)

Max Activating Token Index: 702

Text #11

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8834. Min Act: -0.0000

Data Index: 920434 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8249. Min Act: -0.0000

Data Index: 100081 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1284571 (The Pile)

Max Activating Token Index: 592

Text #14

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1318016 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1946630 (The Pile)

Max Activating Token Index: 826

Text #16

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.7647. Min Act: -0.0000

Data Index: 480435 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.7995. Min Act: -0.0000

Data Index: 561055 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1786172 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1008851 (The Pile)

Max Activating Token Index: 585