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

Dataset: The Pile

Neuron 2609 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5315. Min Range: -4.5315

Max Act: 4.5315. Min Act: -0.0000

Data Index: 1326788 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 4.5315. Min Range: -4.5315

Max Act: 4.2633. Min Act: -0.0000

Data Index: 252760 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.8212. Min Act: -0.0000

Data Index: 1127665 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 4.5315. Min Range: -4.5315

Max Act: 4.0374. Min Act: -0.0000

Data Index: 366352 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.9106. Min Act: -0.0000

Data Index: 867595 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.8823. Min Act: -0.0000

Data Index: 1116660 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.7274. Min Act: -0.0000

Data Index: 823305 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.5705. Min Act: -0.0000

Data Index: 158815 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.5556. Min Act: -0.0000

Data Index: 713162 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.7103. Min Act: -0.0000

Data Index: 484990 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.5834. Min Act: -0.0000

Data Index: 1935120 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.5486. Min Act: -0.0000

Data Index: 1450414 (The Pile)

Max Activating Token Index: 710

Text #12

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.6783. Min Act: -0.0000

Data Index: 1442529 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.6500. Min Act: -0.0000

Data Index: 1365304 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.3480. Min Act: -0.0000

Data Index: 1240640 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.5212. Min Act: -0.0000

Data Index: 390337 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.3520. Min Act: -0.0000

Data Index: 1609413 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.3590. Min Act: -0.0000

Data Index: 1882890 (The Pile)

Max Activating Token Index: 966

Text #18

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.4558. Min Act: -0.0000

Data Index: 380946 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 4.5315. Min Range: -4.5315

Max Act: 3.6370. Min Act: -0.0000

Data Index: 1603572 (The Pile)

Max Activating Token Index: 621