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

Dataset: The Pile

Neuron 4470 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: 0.8607. Min Range: -0.8607

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1903426 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1823780 (The Pile)

Max Activating Token Index: 740

Text #2

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7383. Min Act: -0.0000

Data Index: 1647780 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7504. Min Act: -0.0000

Data Index: 690761 (The Pile)

Max Activating Token Index: 186

Text #4

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7617. Min Act: -0.0000

Data Index: 425416 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7651. Min Act: -0.0000

Data Index: 678794 (The Pile)

Max Activating Token Index: 345

Text #6

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7199. Min Act: -0.0000

Data Index: 334289 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1530118 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1390043 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1036158 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1803391 (The Pile)

Max Activating Token Index: 971

Text #11

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6721. Min Act: -0.0000

Data Index: 458053 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7342. Min Act: -0.0000

Data Index: 480138 (The Pile)

Max Activating Token Index: 53

Text #13

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1748027 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7237. Min Act: -0.0000

Data Index: 805072 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1887650 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1012733 (The Pile)

Max Activating Token Index: 387

Text #17

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6843. Min Act: -0.0000

Data Index: 224395 (The Pile)

Max Activating Token Index: 629

Text #18

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6790. Min Act: -0.0000

Data Index: 518012 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5990. Min Act: -0.0000

Data Index: 736552 (The Pile)

Max Activating Token Index: 504