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

Dataset: The Pile

Neuron 1536 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: 3.7190. Min Range: -3.7190

Max Act: 3.7190. Min Act: -0.0000

Data Index: 1384672 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 3.7190. Min Range: -3.7190

Max Act: 3.6984. Min Act: -0.0000

Data Index: 1900324 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 3.7190. Min Range: -3.7190

Max Act: 3.6724. Min Act: -0.0000

Data Index: 1847845 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 3.7190. Min Range: -3.7190

Max Act: 3.4111. Min Act: -0.0000

Data Index: 1618539 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 3.7190. Min Range: -3.7190

Max Act: 3.4182. Min Act: -0.0000

Data Index: 735123 (The Pile)

Max Activating Token Index: 267

Text #5

Max Range: 3.7190. Min Range: -3.7190

Max Act: 3.0633. Min Act: -0.0000

Data Index: 849381 (The Pile)

Max Activating Token Index: 57

Text #6

Max Range: 3.7190. Min Range: -3.7190

Max Act: 3.1658. Min Act: -0.0000

Data Index: 1589984 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 3.7190. Min Range: -3.7190

Max Act: 2.8581. Min Act: -0.0000

Data Index: 1167850 (The Pile)

Max Activating Token Index: 239

Text #8

Max Range: 3.7190. Min Range: -3.7190

Max Act: 3.2546. Min Act: -0.0000

Data Index: 1670329 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 3.7190. Min Range: -3.7190

Max Act: 3.3746. Min Act: -0.0000

Data Index: 994539 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 3.7190. Min Range: -3.7190

Max Act: 2.9532. Min Act: -0.0000

Data Index: 845184 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 3.7190. Min Range: -3.7190

Max Act: 2.9295. Min Act: -0.0000

Data Index: 263609 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 3.7190. Min Range: -3.7190

Max Act: 2.5633. Min Act: -0.0000

Data Index: 681555 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 3.7190. Min Range: -3.7190

Max Act: 2.9104. Min Act: -0.0000

Data Index: 1892352 (The Pile)

Max Activating Token Index: 554

Text #14

Max Range: 3.7190. Min Range: -3.7190

Max Act: 2.7755. Min Act: -0.0000

Data Index: 1362408 (The Pile)

Max Activating Token Index: 736

Text #15

Max Range: 3.7190. Min Range: -3.7190

Max Act: 3.0166. Min Act: -0.0000

Data Index: 656677 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 3.7190. Min Range: -3.7190

Max Act: 2.6180. Min Act: -0.0000

Data Index: 93768 (The Pile)

Max Activating Token Index: 854

Text #17

Max Range: 3.7190. Min Range: -3.7190

Max Act: 2.8500. Min Act: -0.0000

Data Index: 1545612 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 3.7190. Min Range: -3.7190

Max Act: 2.9031. Min Act: -0.0000

Data Index: 357567 (The Pile)

Max Activating Token Index: 31

Text #19

Max Range: 3.7190. Min Range: -3.7190

Max Act: 3.1549. Min Act: -0.0000

Data Index: 124853 (The Pile)

Max Activating Token Index: 156