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

Dataset: The Pile

Neuron 634 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: 0.6576. Min Range: -0.6576

Max Act: 0.6576. Min Act: -0.0000

Data Index: 737066 (The Pile)

Max Activating Token Index: 857

Text #1

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.5145. Min Act: -0.0000

Data Index: 594176 (The Pile)

Max Activating Token Index: 718

Text #2

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4697. Min Act: -0.0000

Data Index: 626662 (The Pile)

Max Activating Token Index: 600

Text #3

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1837636 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4519. Min Act: -0.0000

Data Index: 798312 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4252. Min Act: -0.0000

Data Index: 943594 (The Pile)

Max Activating Token Index: 247

Text #6

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1083945 (The Pile)

Max Activating Token Index: 488

Text #7

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1970290 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1246901 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1672992 (The Pile)

Max Activating Token Index: 853

Text #10

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4280. Min Act: -0.0000

Data Index: 417637 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1468376 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1228187 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3697. Min Act: -0.0000

Data Index: 437292 (The Pile)

Max Activating Token Index: 359

Text #14

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3793. Min Act: -0.0000

Data Index: 774310 (The Pile)

Max Activating Token Index: 419

Text #15

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4017. Min Act: -0.0000

Data Index: 790900 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3476. Min Act: -0.0000

Data Index: 557615 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3635. Min Act: -0.0000

Data Index: 655928 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1614014 (The Pile)

Max Activating Token Index: 550

Text #19

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3375. Min Act: -0.0000

Data Index: 461425 (The Pile)

Max Activating Token Index: 402