Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 771 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0004

Data Index: 530169 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0825. Min Act: -0.0004

Data Index: 43311 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0783. Min Act: -0.0004

Data Index: 897501 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0832. Min Act: -0.0004

Data Index: 1049403 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0781. Min Act: -0.0004

Data Index: 1611611 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0763. Min Act: -0.0004

Data Index: 1597303 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0822. Min Act: -0.0004

Data Index: 439559 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0780. Min Act: -0.0004

Data Index: 1764345 (The Pile)

Max Activating Token Index: 510

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0786. Min Act: -0.0004

Data Index: 818824 (The Pile)

Max Activating Token Index: 89

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0822. Min Act: -0.0004

Data Index: 1557395 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0762. Min Act: -0.0004

Data Index: 1689661 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0784. Min Act: -0.0004

Data Index: 661932 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0759. Min Act: -0.0004

Data Index: 212978 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0727. Min Act: -0.0004

Data Index: 1794456 (The Pile)

Max Activating Token Index: 249

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0726. Min Act: -0.0004

Data Index: 819959 (The Pile)

Max Activating Token Index: 387

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0754. Min Act: -0.0004

Data Index: 446467 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0685. Min Act: -0.0004

Data Index: 805182 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0747. Min Act: -0.0004

Data Index: 1207569 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0773. Min Act: -0.0004

Data Index: 977269 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0726. Min Act: -0.0004

Data Index: 240118 (The Pile)

Max Activating Token Index: 5