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

Dataset: The Pile

Neuron 4715 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: 3.5952. Min Range: -3.5952

Max Act: 3.5952. Min Act: -0.0000

Data Index: 135565 (The Pile)

Max Activating Token Index: 62

Text #1

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.5912. Min Act: -0.0000

Data Index: 235874 (The Pile)

Max Activating Token Index: 802

Text #2

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.5238. Min Act: -0.0000

Data Index: 888041 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.2983. Min Act: -0.0000

Data Index: 1102288 (The Pile)

Max Activating Token Index: 88

Text #4

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.4319. Min Act: -0.0000

Data Index: 683035 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.5949. Min Act: -0.0000

Data Index: 1570651 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.5907. Min Act: -0.0000

Data Index: 767019 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.2548. Min Act: -0.0000

Data Index: 1850739 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.2634. Min Act: -0.0000

Data Index: 1163240 (The Pile)

Max Activating Token Index: 171

Text #9

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9587. Min Act: -0.0000

Data Index: 927860 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1486. Min Act: -0.0000

Data Index: 1551184 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.4341. Min Act: -0.0000

Data Index: 372361 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9892. Min Act: -0.0000

Data Index: 1370209 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9127. Min Act: -0.0000

Data Index: 554041 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.8635. Min Act: -0.0000

Data Index: 656553 (The Pile)

Max Activating Token Index: 734

Text #15

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9786. Min Act: -0.0000

Data Index: 791822 (The Pile)

Max Activating Token Index: 782

Text #16

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.6857. Min Act: -0.0000

Data Index: 603931 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.0421. Min Act: -0.0000

Data Index: 127020 (The Pile)

Max Activating Token Index: 247

Text #18

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.8751. Min Act: -0.0000

Data Index: 1753882 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.8467. Min Act: -0.0000

Data Index: 601412 (The Pile)

Max Activating Token Index: 55