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

Dataset: The Pile

Neuron 2113 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: 4.2931. Min Range: -4.2931

Max Act: 4.2931. Min Act: -0.0000

Data Index: 925198 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.0965. Min Act: -0.0000

Data Index: 1880130 (The Pile)

Max Activating Token Index: 635

Text #2

Max Range: 4.2931. Min Range: -4.2931

Max Act: 4.0493. Min Act: -0.0000

Data Index: 560752 (The Pile)

Max Activating Token Index: 444

Text #3

Max Range: 4.2931. Min Range: -4.2931

Max Act: 3.7027. Min Act: -0.0000

Data Index: 436447 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 4.2931. Min Range: -4.2931

Max Act: 3.6410. Min Act: -0.0000

Data Index: 1616711 (The Pile)

Max Activating Token Index: 950

Text #5

Max Range: 4.2931. Min Range: -4.2931

Max Act: 3.7601. Min Act: -0.0000

Data Index: 829437 (The Pile)

Max Activating Token Index: 347

Text #6

Max Range: 4.2931. Min Range: -4.2931

Max Act: 3.9245. Min Act: -0.0000

Data Index: 561472 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 4.2931. Min Range: -4.2931

Max Act: 3.5741. Min Act: -0.0000

Data Index: 80877 (The Pile)

Max Activating Token Index: 196

Text #8

Max Range: 4.2931. Min Range: -4.2931

Max Act: 3.7115. Min Act: -0.0000

Data Index: 931651 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 4.2931. Min Range: -4.2931

Max Act: 3.2923. Min Act: -0.0000

Data Index: 1912879 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 4.2931. Min Range: -4.2931

Max Act: 3.0717. Min Act: -0.0000

Data Index: 1509138 (The Pile)

Max Activating Token Index: 335

Text #11

Max Range: 4.2931. Min Range: -4.2931

Max Act: 3.2537. Min Act: -0.0000

Data Index: 115731 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 4.2931. Min Range: -4.2931

Max Act: 3.0837. Min Act: -0.0000

Data Index: 1804727 (The Pile)

Max Activating Token Index: 890

Text #13

Max Range: 4.2931. Min Range: -4.2931

Max Act: 2.9587. Min Act: -0.0000

Data Index: 988041 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 4.2931. Min Range: -4.2931

Max Act: 3.0792. Min Act: -0.0000

Data Index: 996647 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 4.2931. Min Range: -4.2931

Max Act: 2.9450. Min Act: -0.0000

Data Index: 123999 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 4.2931. Min Range: -4.2931

Max Act: 2.7179. Min Act: -0.0000

Data Index: 1182429 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 4.2931. Min Range: -4.2931

Max Act: 2.7744. Min Act: -0.0000

Data Index: 364264 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 4.2931. Min Range: -4.2931

Max Act: 2.8122. Min Act: -0.0000

Data Index: 869810 (The Pile)

Max Activating Token Index: 823

Text #19

Max Range: 4.2931. Min Range: -4.2931

Max Act: 2.6013. Min Act: -0.0000

Data Index: 607256 (The Pile)

Max Activating Token Index: 892