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

Dataset: The Pile

Neuron 4162 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: 1.8017. Min Range: -1.8017

Max Act: 1.3743. Min Act: -0.0000

Data Index: 236624 (The Pile)

Max Activating Token Index: 966

Text #1

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6247. Min Act: -0.0000

Data Index: 1992193 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.8017. Min Act: -0.0000

Data Index: 357965 (The Pile)

Max Activating Token Index: 615

Text #3

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5685. Min Act: -0.0000

Data Index: 808426 (The Pile)

Max Activating Token Index: 584

Text #4

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5317. Min Act: -0.0000

Data Index: 1533116 (The Pile)

Max Activating Token Index: 357

Text #5

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5908. Min Act: -0.0000

Data Index: 1957251 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.5588. Min Act: -0.0000

Data Index: 1261981 (The Pile)

Max Activating Token Index: 284

Text #7

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4986. Min Act: -0.0000

Data Index: 431387 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4398. Min Act: -0.0000

Data Index: 672578 (The Pile)

Max Activating Token Index: 520

Text #9

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4510. Min Act: -0.0000

Data Index: 753560 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4997. Min Act: -0.0000

Data Index: 1586842 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4909. Min Act: -0.0000

Data Index: 689155 (The Pile)

Max Activating Token Index: 979

Text #12

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.3872. Min Act: -0.0000

Data Index: 938581 (The Pile)

Max Activating Token Index: 330

Text #13

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1100160 (The Pile)

Max Activating Token Index: 983

Text #14

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.3791. Min Act: -0.0000

Data Index: 492280 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.3924. Min Act: -0.0000

Data Index: 123198 (The Pile)

Max Activating Token Index: 623

Text #16

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.4135. Min Act: -0.0000

Data Index: 1430582 (The Pile)

Max Activating Token Index: 181

Text #17

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.2848. Min Act: -0.0000

Data Index: 4180 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.3051. Min Act: -0.0000

Data Index: 380823 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.2375. Min Act: -0.0000

Data Index: 371504 (The Pile)

Max Activating Token Index: 840