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

Dataset: The Pile

Neuron 3851 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: 0.6156. Min Range: -0.6156

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1983310 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5021. Min Act: -0.0000

Data Index: 357519 (The Pile)

Max Activating Token Index: 783

Text #2

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1558535 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5527. Min Act: -0.0000

Data Index: 131043 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4914. Min Act: -0.0000

Data Index: 609796 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4748. Min Act: -0.0000

Data Index: 160217 (The Pile)

Max Activating Token Index: 818

Text #6

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1501161 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4334. Min Act: -0.0000

Data Index: 788442 (The Pile)

Max Activating Token Index: 598

Text #8

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5011. Min Act: -0.0000

Data Index: 342115 (The Pile)

Max Activating Token Index: 501

Text #9

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1995245 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4622. Min Act: -0.0000

Data Index: 547505 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1920342 (The Pile)

Max Activating Token Index: 265

Text #12

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.3602. Min Act: -0.0000

Data Index: 252578 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1814172 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4390. Min Act: -0.0000

Data Index: 124274 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4485. Min Act: -0.0000

Data Index: 942314 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1860699 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1256526 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1837305 (The Pile)

Max Activating Token Index: 847

Text #19

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1839996 (The Pile)

Max Activating Token Index: 786