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

Dataset: The Pile

Neuron 3777 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: 4.5108. Min Range: -4.5108

Max Act: 4.5108. Min Act: -0.0000

Data Index: 1667598 (The Pile)

Max Activating Token Index: 981

Text #1

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.0922. Min Act: -0.0000

Data Index: 1921121 (The Pile)

Max Activating Token Index: 545

Text #2

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.2227. Min Act: -0.0000

Data Index: 1750962 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 4.5108. Min Range: -4.5108

Max Act: 4.0042. Min Act: -0.0000

Data Index: 938775 (The Pile)

Max Activating Token Index: 424

Text #4

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.8129. Min Act: -0.0000

Data Index: 1863209 (The Pile)

Max Activating Token Index: 972

Text #5

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.9786. Min Act: -0.0000

Data Index: 898674 (The Pile)

Max Activating Token Index: 901

Text #6

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.6013. Min Act: -0.0000

Data Index: 1033626 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.5214. Min Act: -0.0000

Data Index: 1605686 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.5840. Min Act: -0.0000

Data Index: 1404355 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.8596. Min Act: -0.0000

Data Index: 917401 (The Pile)

Max Activating Token Index: 364

Text #10

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.0515. Min Act: -0.0000

Data Index: 601399 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 4.5108. Min Range: -4.5108

Max Act: 2.8533. Min Act: -0.0000

Data Index: 1740207 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.3431. Min Act: -0.0000

Data Index: 1455051 (The Pile)

Max Activating Token Index: 542

Text #13

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.0755. Min Act: -0.0000

Data Index: 694903 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.2052. Min Act: -0.0000

Data Index: 117048 (The Pile)

Max Activating Token Index: 542

Text #15

Max Range: 4.5108. Min Range: -4.5108

Max Act: 2.9985. Min Act: -0.0000

Data Index: 613154 (The Pile)

Max Activating Token Index: 311

Text #16

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.1313. Min Act: -0.0000

Data Index: 1326351 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.1114. Min Act: -0.0000

Data Index: 923137 (The Pile)

Max Activating Token Index: 767

Text #18

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.0887. Min Act: -0.0000

Data Index: 1455713 (The Pile)

Max Activating Token Index: 788

Text #19

Max Range: 4.5108. Min Range: -4.5108

Max Act: 3.1797. Min Act: -0.0000

Data Index: 1760421 (The Pile)

Max Activating Token Index: 592