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

Dataset: The Pile

Neuron 529 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: 1.7798. Min Range: -1.7798

Max Act: 1.7798. Min Act: -0.0000

Data Index: 138168 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.7295. Min Act: -0.0000

Data Index: 1779255 (The Pile)

Max Activating Token Index: 3

Text #2

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.5426. Min Act: -0.0000

Data Index: 629671 (The Pile)

Max Activating Token Index: 657

Text #3

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.5614. Min Act: -0.0000

Data Index: 396322 (The Pile)

Max Activating Token Index: 857

Text #4

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.5160. Min Act: -0.0000

Data Index: 1666728 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.4972. Min Act: -0.0000

Data Index: 1591656 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.4800. Min Act: -0.0000

Data Index: 1326188 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3942. Min Act: -0.0000

Data Index: 701871 (The Pile)

Max Activating Token Index: 769

Text #8

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3997. Min Act: -0.0000

Data Index: 331293 (The Pile)

Max Activating Token Index: 264

Text #9

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3684. Min Act: -0.0000

Data Index: 1070278 (The Pile)

Max Activating Token Index: 900

Text #10

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3076. Min Act: -0.0000

Data Index: 1242832 (The Pile)

Max Activating Token Index: 911

Text #11

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1847347 (The Pile)

Max Activating Token Index: 778

Text #12

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3311. Min Act: -0.0000

Data Index: 1579263 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3165. Min Act: -0.0000

Data Index: 1065076 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3912. Min Act: -0.0000

Data Index: 415351 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3925. Min Act: -0.0000

Data Index: 987545 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1213950 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3312. Min Act: -0.0000

Data Index: 827436 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3735. Min Act: -0.0000

Data Index: 1264306 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.4127. Min Act: -0.0000

Data Index: 1218006 (The Pile)

Max Activating Token Index: 711