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

Dataset: The Pile

Neuron 101 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: 0.7970. Min Range: -0.7970

Max Act: 0.7970. Min Act: -0.0000

Data Index: 730094 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1700667 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1208652 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6005. Min Act: -0.0000

Data Index: 391440 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1344950 (The Pile)

Max Activating Token Index: 63

Text #5

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5556. Min Act: -0.0000

Data Index: 507761 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5798. Min Act: -0.0000

Data Index: 906367 (The Pile)

Max Activating Token Index: 538

Text #7

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1047902 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6053. Min Act: -0.0000

Data Index: 74766 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5664. Min Act: -0.0000

Data Index: 103763 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5389. Min Act: -0.0000

Data Index: 401540 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1179409 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5375. Min Act: -0.0000

Data Index: 201508 (The Pile)

Max Activating Token Index: 762

Text #13

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1561983 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1192150 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5079. Min Act: -0.0000

Data Index: 823411 (The Pile)

Max Activating Token Index: 516

Text #16

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1477079 (The Pile)

Max Activating Token Index: 605

Text #17

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1633249 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1093655 (The Pile)

Max Activating Token Index: 348

Text #19

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5126. Min Act: -0.0000

Data Index: 550890 (The Pile)

Max Activating Token Index: 537