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

Dataset: The Pile

Neuron 2172 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.3175. Min Act: -0.0000

Data Index: 269796 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.2471. Min Act: -0.0000

Data Index: 1048441 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1715. Min Act: -0.0000

Data Index: 146384 (The Pile)

Max Activating Token Index: 524

Text #3

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1339444 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0874. Min Act: -0.0000

Data Index: 1979625 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1567040 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0067. Min Act: -0.0000

Data Index: 4869 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9936. Min Act: -0.0000

Data Index: 929348 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1413089 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1494516 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1819583 (The Pile)

Max Activating Token Index: 844

Text #11

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9825. Min Act: -0.0000

Data Index: 1029323 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9692. Min Act: -0.0000

Data Index: 547013 (The Pile)

Max Activating Token Index: 514

Text #13

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9690. Min Act: -0.0000

Data Index: 390960 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9688. Min Act: -0.0000

Data Index: 887995 (The Pile)

Max Activating Token Index: 938

Text #15

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.8970. Min Act: -0.0000

Data Index: 846315 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0121. Min Act: -0.0000

Data Index: 232846 (The Pile)

Max Activating Token Index: 345

Text #17

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1022519 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1681474 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1767615 (The Pile)

Max Activating Token Index: 601