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

Dataset: The Pile

Neuron 3696 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: 0.4613. Min Range: -0.4613

Max Act: 0.4613. Min Act: -0.0000

Data Index: 798541 (The Pile)

Max Activating Token Index: 140

Text #1

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.4408. Min Act: 0.0000

Data Index: 1461227 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.4053. Min Act: 0.0000

Data Index: 746883 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3686. Min Act: -0.0000

Data Index: 848389 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1967554 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3309. Min Act: -0.0000

Data Index: 669610 (The Pile)

Max Activating Token Index: 602

Text #6

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3170. Min Act: 0.0000

Data Index: 1924590 (The Pile)

Max Activating Token Index: 657

Text #7

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3191. Min Act: -0.0000

Data Index: 196482 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1193402 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3236. Min Act: 0.0000

Data Index: 827523 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3131. Min Act: -0.0000

Data Index: 521016 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1900290 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3159. Min Act: -0.0000

Data Index: 319071 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3090. Min Act: -0.0000

Data Index: 765158 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3107. Min Act: -0.0000

Data Index: 357732 (The Pile)

Max Activating Token Index: 921

Text #15

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.2932. Min Act: -0.0000

Data Index: 230443 (The Pile)

Max Activating Token Index: 337

Text #16

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3113. Min Act: -0.0000

Data Index: 376396 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.2994. Min Act: 0.0000

Data Index: 422718 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1117804 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1060353 (The Pile)

Max Activating Token Index: 265