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

Dataset: The Pile

Neuron 3703 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1345. Min Range: -3.1345

Max Act: 3.1345. Min Act: -0.0000

Data Index: 191305 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.9450. Min Act: -0.0000

Data Index: 169033 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.6056. Min Act: -0.0000

Data Index: 1193993 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.7954. Min Act: -0.0000

Data Index: 373712 (The Pile)

Max Activating Token Index: 504

Text #4

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.6964. Min Act: -0.0000

Data Index: 1012246 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 3.1345. Min Range: -3.1345

Max Act: 2.0727. Min Act: -0.0000

Data Index: 1150489 (The Pile)

Max Activating Token Index: 956

Text #6

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1463743 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1601148 (The Pile)

Max Activating Token Index: 482

Text #8

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.6673. Min Act: -0.0000

Data Index: 1559202 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.2318. Min Act: -0.0000

Data Index: 323869 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.3495. Min Act: -0.0000

Data Index: 1992188 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.2646. Min Act: -0.0000

Data Index: 255077 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.2736. Min Act: -0.0000

Data Index: 852095 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5397. Min Act: -0.0000

Data Index: 78669 (The Pile)

Max Activating Token Index: 846

Text #14

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5223. Min Act: -0.0000

Data Index: 532771 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.1877. Min Act: -0.0000

Data Index: 1239501 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.4396. Min Act: -0.0000

Data Index: 1818886 (The Pile)

Max Activating Token Index: 930

Text #17

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1762363 (The Pile)

Max Activating Token Index: 520

Text #18

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1451241 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 3.1345. Min Range: -3.1345

Max Act: 1.1587. Min Act: -0.0000

Data Index: 470549 (The Pile)

Max Activating Token Index: 950