Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2013 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.7084. Min Act: -0.0000

Data Index: 412488 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6165. Min Act: -0.0000

Data Index: 400099 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6442. Min Act: -0.0000

Data Index: 791599 (The Pile)

Max Activating Token Index: 675

Text #3

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1031917 (The Pile)

Max Activating Token Index: 725

Text #4

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6108. Min Act: -0.0000

Data Index: 118422 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1165319 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1934064 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5831. Min Act: -0.0000

Data Index: 623471 (The Pile)

Max Activating Token Index: 328

Text #8

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5852. Min Act: -0.0000

Data Index: 851257 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1580952 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1122836 (The Pile)

Max Activating Token Index: 876

Text #11

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1291837 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5723. Min Act: -0.0000

Data Index: 60374 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5503. Min Act: -0.0000

Data Index: 402894 (The Pile)

Max Activating Token Index: 381

Text #14

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1458836 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5754. Min Act: -0.0000

Data Index: 63837 (The Pile)

Max Activating Token Index: 295

Text #16

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1798653 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5847. Min Act: -0.0000

Data Index: 644764 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1564891 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5093. Min Act: -0.0000

Data Index: 695686 (The Pile)

Max Activating Token Index: 70