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

Dataset: The Pile

Neuron 4332 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: 0.8686. Min Range: -0.8686

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1079767 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1673629 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.5764. Min Act: -0.0000

Data Index: 959969 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.5354. Min Act: 0.0000

Data Index: 278011 (The Pile)

Max Activating Token Index: 59

Text #4

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1896914 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1167804 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1232241 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1521663 (The Pile)

Max Activating Token Index: 251

Text #8

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.5094. Min Act: -0.0000

Data Index: 96684 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1773122 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.5046. Min Act: -0.0000

Data Index: 294491 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.4371. Min Act: -0.0000

Data Index: 547203 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.4763. Min Act: 0.0000

Data Index: 1231255 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1007873 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.4601. Min Act: 0.0000

Data Index: 326916 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1639111 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1627943 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.4522. Min Act: -0.0000

Data Index: 394059 (The Pile)

Max Activating Token Index: 797

Text #18

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1435091 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.4329. Min Act: -0.0000

Data Index: 485698 (The Pile)

Max Activating Token Index: 230