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

Dataset: The Pile

Neuron 3496 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: 0.1151. Min Range: -0.1151

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1082126 (The Pile)

Max Activating Token Index: 73

Text #1

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1135. Min Act: -0.0000

Data Index: 211836 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1580091 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1095. Min Act: -0.0000

Data Index: 463006 (The Pile)

Max Activating Token Index: 540

Text #4

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1617328 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1012. Min Act: -0.0000

Data Index: 317495 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0977. Min Act: -0.0000

Data Index: 34330 (The Pile)

Max Activating Token Index: 138

Text #7

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1747733 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0959. Min Act: -0.0000

Data Index: 677719 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0979. Min Act: -0.0000

Data Index: 689654 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0952. Min Act: -0.0000

Data Index: 284860 (The Pile)

Max Activating Token Index: 698

Text #11

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1929967 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1715652 (The Pile)

Max Activating Token Index: 94

Text #13

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0784. Min Act: -0.0000

Data Index: 327235 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1995056 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0900. Min Act: -0.0000

Data Index: 17332 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1874216 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0872. Min Act: -0.0000

Data Index: 758482 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0784. Min Act: -0.0000

Data Index: 586061 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0779. Min Act: -0.0000

Data Index: 933785 (The Pile)

Max Activating Token Index: 83