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

Dataset: The Pile

Neuron 2820 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: 0.7069. Min Range: -0.7069

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1260408 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6217. Min Act: -0.0000

Data Index: 924487 (The Pile)

Max Activating Token Index: 903

Text #2

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5852. Min Act: -0.0000

Data Index: 617851 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1931345 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6017. Min Act: -0.0000

Data Index: 212682 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5756. Min Act: -0.0000

Data Index: 786609 (The Pile)

Max Activating Token Index: 722

Text #6

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5537. Min Act: -0.0000

Data Index: 254940 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5043. Min Act: -0.0000

Data Index: 674084 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5314. Min Act: -0.0000

Data Index: 16347 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5747. Min Act: -0.0000

Data Index: 366247 (The Pile)

Max Activating Token Index: 819

Text #10

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5300. Min Act: -0.0000

Data Index: 152667 (The Pile)

Max Activating Token Index: 871

Text #11

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1809743 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1959660 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4710. Min Act: -0.0000

Data Index: 76734 (The Pile)

Max Activating Token Index: 845

Text #14

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1606235 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5231. Min Act: -0.0000

Data Index: 134467 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1183541 (The Pile)

Max Activating Token Index: 414

Text #17

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1607765 (The Pile)

Max Activating Token Index: 563

Text #18

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4656. Min Act: -0.0000

Data Index: 1711746 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5088. Min Act: -0.0000

Data Index: 915205 (The Pile)

Max Activating Token Index: 1003