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

Dataset: The Pile

Neuron 3395 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: 0.5074. Min Range: -0.5074

Max Act: 0.5074. Min Act: -0.0000

Data Index: 740405 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3786. Min Act: -0.0000

Data Index: 774631 (The Pile)

Max Activating Token Index: 126

Text #2

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1721383 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3495. Min Act: -0.0000

Data Index: 865359 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1292854 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3449. Min Act: -0.0000

Data Index: 1137622 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1231744 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1807574 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3489. Min Act: -0.0000

Data Index: 712368 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1468026 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3122. Min Act: -0.0000

Data Index: 1021527 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1668836 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.2997. Min Act: -0.0000

Data Index: 541304 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.2606. Min Act: -0.0000

Data Index: 495791 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3040. Min Act: -0.0000

Data Index: 217919 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1719026 (The Pile)

Max Activating Token Index: 729

Text #16

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.2499. Min Act: -0.0000

Data Index: 435285 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1475924 (The Pile)

Max Activating Token Index: 845

Text #18

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.2700. Min Act: -0.0000

Data Index: 479184 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1645083 (The Pile)

Max Activating Token Index: 825