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

Dataset: The Pile

Neuron 2576 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1402119 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.4330. Min Act: -0.0000

Data Index: 846151 (The Pile)

Max Activating Token Index: 270

Text #2

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1623816 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.4256. Min Act: -0.0000

Data Index: 44057 (The Pile)

Max Activating Token Index: 738

Text #4

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3966. Min Act: -0.0000

Data Index: 615895 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1726027 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.4273. Min Act: -0.0000

Data Index: 493731 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3723. Min Act: -0.0000

Data Index: 248800 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1576576 (The Pile)

Max Activating Token Index: 736

Text #9

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3766. Min Act: -0.0000

Data Index: 108309 (The Pile)

Max Activating Token Index: 463

Text #10

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1787013 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1617119 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3814. Min Act: -0.0000

Data Index: 23663 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1633305 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1766526 (The Pile)

Max Activating Token Index: 819

Text #15

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1116134 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3533. Min Act: -0.0000

Data Index: 313602 (The Pile)

Max Activating Token Index: 594

Text #17

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1800415 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1379215 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3741. Min Act: -0.0000

Data Index: 242986 (The Pile)

Max Activating Token Index: 920