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

Dataset: The Pile

Neuron 1709 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: 0.4096. Min Range: -0.4096

Max Act: 0.4096. Min Act: -0.0000

Data Index: 85747 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1792040 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.3413. Min Act: -0.0000

Data Index: 463224 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.3291. Min Act: -0.0000

Data Index: 159454 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.3062. Min Act: -0.0000

Data Index: 575025 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1603827 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.3114. Min Act: -0.0000

Data Index: 532512 (The Pile)

Max Activating Token Index: 324

Text #7

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1154813 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2919. Min Act: -0.0000

Data Index: 891822 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.3019. Min Act: -0.0000

Data Index: 577674 (The Pile)

Max Activating Token Index: 516

Text #10

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1924162 (The Pile)

Max Activating Token Index: 645

Text #11

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2900. Min Act: -0.0000

Data Index: 283786 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2927. Min Act: -0.0000

Data Index: 544894 (The Pile)

Max Activating Token Index: 76

Text #13

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2984. Min Act: -0.0000

Data Index: 147060 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1825453 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1574108 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2756. Min Act: -0.0000

Data Index: 876690 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2742. Min Act: -0.0000

Data Index: 593457 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1952306 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2819. Min Act: -0.0000

Data Index: 908313 (The Pile)

Max Activating Token Index: 936