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

Dataset: The Pile

Neuron 2886 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.7481. Min Act: -0.0000

Data Index: 157275 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.7704. Min Act: 0.0000

Data Index: 1961100 (The Pile)

Max Activating Token Index: 600

Text #2

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1111093 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.7211. Min Act: -0.0000

Data Index: 889111 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6652. Min Act: -0.0000

Data Index: 925678 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1210162 (The Pile)

Max Activating Token Index: 802

Text #6

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6457. Min Act: -0.0000

Data Index: 977797 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1036806 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6132. Min Act: -0.0000

Data Index: 361470 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6026. Min Act: 0.0000

Data Index: 568556 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1195177 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1628909 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1012801 (The Pile)

Max Activating Token Index: 909

Text #13

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5562. Min Act: -0.0000

Data Index: 891336 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1194223 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5844. Min Act: -0.0000

Data Index: 280877 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5645. Min Act: -0.0000

Data Index: 965685 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5614. Min Act: 0.0000

Data Index: 1810521 (The Pile)

Max Activating Token Index: 669

Text #18

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1096386 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5384. Min Act: -0.0000

Data Index: 63992 (The Pile)

Max Activating Token Index: 397