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

Dataset: The Pile

Neuron 3963 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: 0.5544. Min Range: -0.5544

Max Act: 0.5544. Min Act: -0.0000

Data Index: 168755 (The Pile)

Max Activating Token Index: 30

Text #1

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4671. Min Act: -0.0000

Data Index: 448810 (The Pile)

Max Activating Token Index: 997

Text #2

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1986901 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1090873 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1607455 (The Pile)

Max Activating Token Index: 7

Text #5

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1820234 (The Pile)

Max Activating Token Index: 458

Text #6

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4496. Min Act: -0.0000

Data Index: 566543 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1851401 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4685. Min Act: -0.0000

Data Index: 1723606 (The Pile)

Max Activating Token Index: 705

Text #9

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4694. Min Act: -0.0000

Data Index: 822536 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4566. Min Act: -0.0000

Data Index: 402132 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4504. Min Act: -0.0000

Data Index: 505227 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4497. Min Act: -0.0000

Data Index: 992556 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1586403 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1899926 (The Pile)

Max Activating Token Index: 683

Text #15

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4536. Min Act: -0.0000

Data Index: 847777 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1123113 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4333. Min Act: -0.0000

Data Index: 445747 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1787203 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4469. Min Act: -0.0000

Data Index: 210860 (The Pile)

Max Activating Token Index: 29