Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1020 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.8896. Min Act: -0.0000

Data Index: 806135 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1545570 (The Pile)

Max Activating Token Index: 794

Text #2

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1039166 (The Pile)

Max Activating Token Index: 909

Text #3

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1470064 (The Pile)

Max Activating Token Index: 303

Text #4

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.7646. Min Act: -0.0000

Data Index: 412423 (The Pile)

Max Activating Token Index: 81

Text #5

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.7360. Min Act: -0.0000

Data Index: 694818 (The Pile)

Max Activating Token Index: 203

Text #6

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1980916 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6332. Min Act: -0.0000

Data Index: 611805 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6879. Min Act: -0.0000

Data Index: 687371 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6000. Min Act: -0.0000

Data Index: 386563 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5731. Min Act: -0.0000

Data Index: 327674 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1284473 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1720173 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1284431 (The Pile)

Max Activating Token Index: 649

Text #14

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1897842 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5677. Min Act: -0.0000

Data Index: 117446 (The Pile)

Max Activating Token Index: 388

Text #16

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5474. Min Act: -0.0000

Data Index: 293511 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1054816 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1409365 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 0.8896. Min Range: -0.8896

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1985574 (The Pile)

Max Activating Token Index: 106