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

Dataset: The Pile

Neuron 2982 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1757. Min Act: -0.0000

Data Index: 730045 (The Pile)

Max Activating Token Index: 184

Text #1

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1269. Min Act: -0.0000

Data Index: 1123017 (The Pile)

Max Activating Token Index: 851

Text #2

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0981. Min Act: -0.0000

Data Index: 715531 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1483712 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1702989 (The Pile)

Max Activating Token Index: 309

Text #5

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0853. Min Act: -0.0000

Data Index: 759570 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1600800 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1399988 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0839. Min Act: -0.0000

Data Index: 5641 (The Pile)

Max Activating Token Index: 183

Text #9

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0905. Min Act: -0.0000

Data Index: 932484 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0835. Min Act: -0.0000

Data Index: 333631 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1559896 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0808. Min Act: -0.0000

Data Index: 693068 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0789. Min Act: -0.0000

Data Index: 667377 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1717881 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0857. Min Act: -0.0000

Data Index: 261635 (The Pile)

Max Activating Token Index: 486

Text #16

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1830570 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0817. Min Act: -0.0000

Data Index: 459087 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0698. Min Act: -0.0000

Data Index: 864319 (The Pile)

Max Activating Token Index: 669

Text #19

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.0729. Min Act: -0.0000

Data Index: 929069 (The Pile)

Max Activating Token Index: 589