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

Dataset: The Pile

Neuron 2478 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: 8.1889. Min Range: -8.1889

Max Act: 8.1889. Min Act: -0.0000

Data Index: 959609 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 8.1889. Min Range: -8.1889

Max Act: 8.1889. Min Act: -0.0000

Data Index: 858863 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 8.1889. Min Range: -8.1889

Max Act: 8.0379. Min Act: -0.0000

Data Index: 1819358 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 8.1889. Min Range: -8.1889

Max Act: 7.3247. Min Act: -0.0000

Data Index: 335080 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 8.1889. Min Range: -8.1889

Max Act: 6.7638. Min Act: -0.0000

Data Index: 257021 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 8.1889. Min Range: -8.1889

Max Act: 6.9894. Min Act: -0.0000

Data Index: 1634099 (The Pile)

Max Activating Token Index: 743

Text #6

Max Range: 8.1889. Min Range: -8.1889

Max Act: 6.9716. Min Act: -0.0000

Data Index: 1636617 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 8.1889. Min Range: -8.1889

Max Act: 6.5527. Min Act: -0.0000

Data Index: 390060 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 8.1889. Min Range: -8.1889

Max Act: 5.9536. Min Act: -0.0000

Data Index: 1541990 (The Pile)

Max Activating Token Index: 767

Text #9

Max Range: 8.1889. Min Range: -8.1889

Max Act: 5.9581. Min Act: -0.0000

Data Index: 1735857 (The Pile)

Max Activating Token Index: 616

Text #10

Max Range: 8.1889. Min Range: -8.1889

Max Act: 5.7013. Min Act: -0.0000

Data Index: 1117589 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 8.1889. Min Range: -8.1889

Max Act: 6.2363. Min Act: -0.0000

Data Index: 1131327 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 8.1889. Min Range: -8.1889

Max Act: 6.2237. Min Act: -0.0000

Data Index: 1305898 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 8.1889. Min Range: -8.1889

Max Act: 5.7863. Min Act: -0.0000

Data Index: 136343 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 8.1889. Min Range: -8.1889

Max Act: 6.4858. Min Act: -0.0000

Data Index: 1765330 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 8.1889. Min Range: -8.1889

Max Act: 5.8996. Min Act: -0.0000

Data Index: 868380 (The Pile)

Max Activating Token Index: 530

Text #16

Max Range: 8.1889. Min Range: -8.1889

Max Act: 5.4666. Min Act: -0.0000

Data Index: 1598476 (The Pile)

Max Activating Token Index: 234

Text #17

Max Range: 8.1889. Min Range: -8.1889

Max Act: 6.1893. Min Act: -0.0000

Data Index: 1716498 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 8.1889. Min Range: -8.1889

Max Act: 6.4035. Min Act: -0.0000

Data Index: 587044 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 8.1889. Min Range: -8.1889

Max Act: 5.9303. Min Act: -0.0000

Data Index: 1188423 (The Pile)

Max Activating Token Index: 644