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

Dataset: The Pile

Neuron 651 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5796. Min Range: -4.5796

Max Act: 4.5796. Min Act: -0.0000

Data Index: 661408 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 4.5796. Min Range: -4.5796

Max Act: 4.4452. Min Act: -0.0000

Data Index: 1586575 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.8452. Min Act: -0.0000

Data Index: 110321 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.6255. Min Act: -0.0000

Data Index: 581603 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.7713. Min Act: -0.0000

Data Index: 773723 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.5753. Min Act: -0.0000

Data Index: 923256 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.8700. Min Act: -0.0000

Data Index: 207729 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.5068. Min Act: -0.0000

Data Index: 470486 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.7804. Min Act: -0.0000

Data Index: 821373 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.7703. Min Act: -0.0000

Data Index: 1682419 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.4695. Min Act: -0.0000

Data Index: 1177504 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 4.5796. Min Range: -4.5796

Max Act: 4.1007. Min Act: -0.0000

Data Index: 792266 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.5853. Min Act: -0.0000

Data Index: 1704072 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.8634. Min Act: -0.0000

Data Index: 947446 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.5263. Min Act: -0.0000

Data Index: 1840701 (The Pile)

Max Activating Token Index: 718

Text #15

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.8588. Min Act: -0.0000

Data Index: 1100508 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.6685. Min Act: -0.0000

Data Index: 1931947 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.6594. Min Act: -0.0000

Data Index: 1518413 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.4648. Min Act: -0.0000

Data Index: 966627 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 4.5796. Min Range: -4.5796

Max Act: 3.6018. Min Act: -0.0000

Data Index: 1419799 (The Pile)

Max Activating Token Index: 743