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

Dataset: The Pile

Neuron 595 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5065. Min Act: -0.0000

Data Index: 132915 (The Pile)

Max Activating Token Index: 773

Text #1

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4567. Min Act: -0.0000

Data Index: 749415 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5425. Min Act: -0.0000

Data Index: 136881 (The Pile)

Max Activating Token Index: 678

Text #3

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1694607 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1445181 (The Pile)

Max Activating Token Index: 684

Text #5

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4361. Min Act: -0.0000

Data Index: 494290 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1451109 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1849070 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1353078 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1557196 (The Pile)

Max Activating Token Index: 235

Text #10

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4461. Min Act: -0.0000

Data Index: 523471 (The Pile)

Max Activating Token Index: 681

Text #11

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1900213 (The Pile)

Max Activating Token Index: 762

Text #12

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1671185 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3698. Min Act: -0.0000

Data Index: 38971 (The Pile)

Max Activating Token Index: 401

Text #14

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1891024 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4291. Min Act: -0.0000

Data Index: 640078 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1807484 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3961. Min Act: -0.0000

Data Index: 715791 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3258. Min Act: -0.0000

Data Index: 677569 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3941. Min Act: -0.0000

Data Index: 207627 (The Pile)

Max Activating Token Index: 438