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

Dataset: The Pile

Neuron 2017 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: 0.9008. Min Range: -0.9008

Max Act: 0.9008. Min Act: -0.0000

Data Index: 1321266 (The Pile)

Max Activating Token Index: 866

Text #1

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.8591. Min Act: 0.0000

Data Index: 449660 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7100. Min Act: -0.0000

Data Index: 394839 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1429838 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7297. Min Act: -0.0000

Data Index: 528676 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6935. Min Act: -0.0000

Data Index: 193725 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7265. Min Act: -0.0000

Data Index: 361108 (The Pile)

Max Activating Token Index: 569

Text #7

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1625623 (The Pile)

Max Activating Token Index: 259

Text #8

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6495. Min Act: -0.0000

Data Index: 627855 (The Pile)

Max Activating Token Index: 503

Text #9

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6367. Min Act: -0.0000

Data Index: 287373 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1747111 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6883. Min Act: 0.0000

Data Index: 1613722 (The Pile)

Max Activating Token Index: 97

Text #12

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6883. Min Act: 0.0000

Data Index: 744312 (The Pile)

Max Activating Token Index: 836

Text #13

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6005. Min Act: 0.0000

Data Index: 594823 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1490030 (The Pile)

Max Activating Token Index: 221

Text #15

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1678223 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.5841. Min Act: 0.0000

Data Index: 138481 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1964879 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6036. Min Act: -0.0000

Data Index: 115756 (The Pile)

Max Activating Token Index: 487

Text #19

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1688422 (The Pile)

Max Activating Token Index: 476