Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3503 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1009547 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2991. Min Act: -0.0000

Data Index: 423499 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2981. Min Act: -0.0000

Data Index: 227063 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2874. Min Act: -0.0000

Data Index: 349965 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2938. Min Act: -0.0000

Data Index: 732806 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1605357 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1887993 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1620011 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2857. Min Act: -0.0000

Data Index: 624654 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2644. Min Act: -0.0000

Data Index: 504952 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1853102 (The Pile)

Max Activating Token Index: 111

Text #11

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2684. Min Act: -0.0000

Data Index: 312962 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1926672 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2850. Min Act: -0.0000

Data Index: 541851 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1032305 (The Pile)

Max Activating Token Index: 50

Text #15

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1580484 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1123854 (The Pile)

Max Activating Token Index: 792

Text #17

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2626. Min Act: -0.0000

Data Index: 150562 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2632. Min Act: -0.0000

Data Index: 159682 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2527. Min Act: -0.0000

Data Index: 82138 (The Pile)

Max Activating Token Index: 584