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

Dataset: The Pile

Neuron 2721 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: 0.6458. Min Range: -0.6458

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1330277 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1530499 (The Pile)

Max Activating Token Index: 320

Text #2

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6336. Min Act: 0.0000

Data Index: 1948313 (The Pile)

Max Activating Token Index: 967

Text #3

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1411421 (The Pile)

Max Activating Token Index: 43

Text #4

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5741. Min Act: 0.0000

Data Index: 31594 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5510. Min Act: 0.0000

Data Index: 1924928 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5430. Min Act: -0.0000

Data Index: 104829 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5450. Min Act: 0.0000

Data Index: 480805 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1995860 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5530. Min Act: -0.0000

Data Index: 815810 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1874541 (The Pile)

Max Activating Token Index: 226

Text #11

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5115. Min Act: -0.0000

Data Index: 830849 (The Pile)

Max Activating Token Index: 590

Text #12

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1540980 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5022. Min Act: -0.0000

Data Index: 319979 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4835. Min Act: -0.0000

Data Index: 40786 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4738. Min Act: -0.0000

Data Index: 554507 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5303. Min Act: -0.0000

Data Index: 438883 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4730. Min Act: -0.0000

Data Index: 111551 (The Pile)

Max Activating Token Index: 626

Text #18

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1626425 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5016. Min Act: -0.0000

Data Index: 894212 (The Pile)

Max Activating Token Index: 350