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

Dataset: The Pile

Neuron 5097 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: 1.0735. Min Range: -1.0735

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1894811 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1032385 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 1.0735. Min Range: -1.0735

Max Act: 1.0130. Min Act: -0.0000

Data Index: 1693625 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1251885 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.8538. Min Act: -0.0000

Data Index: 415503 (The Pile)

Max Activating Token Index: 382

Text #5

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9171. Min Act: -0.0000

Data Index: 905510 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1490504 (The Pile)

Max Activating Token Index: 702

Text #7

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9441. Min Act: -0.0000

Data Index: 664024 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1214847 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.8786. Min Act: -0.0000

Data Index: 782429 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.8619. Min Act: -0.0000

Data Index: 963642 (The Pile)

Max Activating Token Index: 396

Text #11

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1272994 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1134211 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1187930 (The Pile)

Max Activating Token Index: 153

Text #14

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.8498. Min Act: -0.0000

Data Index: 1716431 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1527581 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.8620. Min Act: -0.0000

Data Index: 220767 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1716629 (The Pile)

Max Activating Token Index: 1022

Text #18

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1428063 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 1.0735. Min Range: -1.0735

Max Act: 0.7868. Min Act: -0.0000

Data Index: 388231 (The Pile)

Max Activating Token Index: 452