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

Dataset: The Pile

Neuron 2043 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 8.2771. Min Range: -8.2771

Max Act: 8.2771. Min Act: -0.0000

Data Index: 1151962 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.8886. Min Act: -0.0000

Data Index: 425118 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 8.2771. Min Range: -8.2771

Max Act: 8.2409. Min Act: -0.0000

Data Index: 952547 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 8.2771. Min Range: -8.2771

Max Act: 8.1481. Min Act: -0.0000

Data Index: 1982412 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 8.2771. Min Range: -8.2771

Max Act: 8.0542. Min Act: -0.0000

Data Index: 1954345 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 8.2771. Min Range: -8.2771

Max Act: 6.9549. Min Act: -0.0000

Data Index: 40875 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.6180. Min Act: -0.0000

Data Index: 1879297 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.7875. Min Act: -0.0000

Data Index: 1881811 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.2854. Min Act: -0.0000

Data Index: 1267164 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.5293. Min Act: -0.0000

Data Index: 1547791 (The Pile)

Max Activating Token Index: 588

Text #10

Max Range: 8.2771. Min Range: -8.2771

Max Act: 6.8263. Min Act: -0.0000

Data Index: 923072 (The Pile)

Max Activating Token Index: 943

Text #11

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.3484. Min Act: -0.0000

Data Index: 1249240 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.1713. Min Act: -0.0000

Data Index: 1658381 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.3761. Min Act: -0.0000

Data Index: 1426523 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.1846. Min Act: -0.0000

Data Index: 1880005 (The Pile)

Max Activating Token Index: 989

Text #15

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.1841. Min Act: -0.0000

Data Index: 972618 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.3768. Min Act: -0.0000

Data Index: 359328 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.7017. Min Act: -0.0000

Data Index: 1092180 (The Pile)

Max Activating Token Index: 707

Text #18

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.1537. Min Act: -0.0000

Data Index: 199828 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 8.2771. Min Range: -8.2771

Max Act: 7.3345. Min Act: -0.0000

Data Index: 46162 (The Pile)

Max Activating Token Index: 820