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

Dataset: The Pile

Neuron 1531 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.6384. Min Act: -0.0000

Data Index: 163986 (The Pile)

Max Activating Token Index: 158

Text #1

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.4958. Min Act: -0.0000

Data Index: 1229341 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.5536. Min Act: -0.0000

Data Index: 689787 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.3983. Min Act: -0.0000

Data Index: 1985548 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.4881. Min Act: -0.0000

Data Index: 859549 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.4675. Min Act: -0.0000

Data Index: 798747 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.4135. Min Act: -0.0000

Data Index: 1887838 (The Pile)

Max Activating Token Index: 884

Text #7

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.4329. Min Act: -0.0000

Data Index: 760219 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.3944. Min Act: -0.0000

Data Index: 1472691 (The Pile)

Max Activating Token Index: 554

Text #9

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.2963. Min Act: -0.0000

Data Index: 898195 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.4820. Min Act: -0.0000

Data Index: 317439 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1898767 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.3576. Min Act: -0.0000

Data Index: 698546 (The Pile)

Max Activating Token Index: 194

Text #13

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.2903. Min Act: -0.0000

Data Index: 90674 (The Pile)

Max Activating Token Index: 240

Text #14

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1606491 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.2660. Min Act: -0.0000

Data Index: 37394 (The Pile)

Max Activating Token Index: 91

Text #16

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1931907 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.3152. Min Act: -0.0000

Data Index: 1980729 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.3221. Min Act: -0.0000

Data Index: 370818 (The Pile)

Max Activating Token Index: 963

Text #19

Max Range: 1.6384. Min Range: -1.6384

Max Act: 1.3087. Min Act: -0.0000

Data Index: 806509 (The Pile)

Max Activating Token Index: 1004