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

Dataset: The Pile

Neuron 3934 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: 0.5684. Min Range: -0.5684

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1511819 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1016730 (The Pile)

Max Activating Token Index: 669

Text #2

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5198. Min Act: -0.0000

Data Index: 333082 (The Pile)

Max Activating Token Index: 188

Text #3

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4971. Min Act: -0.0000

Data Index: 773103 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5499. Min Act: -0.0000

Data Index: 81838 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5684. Min Act: -0.0000

Data Index: 251478 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1249928 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1542885 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1939311 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5092. Min Act: -0.0000

Data Index: 660489 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1742098 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1803089 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4675. Min Act: -0.0000

Data Index: 315326 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1505214 (The Pile)

Max Activating Token Index: 622

Text #14

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1400492 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3867. Min Act: -0.0000

Data Index: 801788 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4735. Min Act: -0.0000

Data Index: 48592 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4358. Min Act: -0.0000

Data Index: 383584 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1196221 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4176. Min Act: -0.0000

Data Index: 629441 (The Pile)

Max Activating Token Index: 759