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

Dataset: The Pile

Neuron 1419 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1932157 (The Pile)

Max Activating Token Index: 736

Text #1

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1825912 (The Pile)

Max Activating Token Index: 574

Text #2

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.4128. Min Act: -0.0000

Data Index: 696759 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1199351 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3737. Min Act: -0.0000

Data Index: 510141 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1138528 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3915. Min Act: -0.0000

Data Index: 977012 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3787. Min Act: -0.0000

Data Index: 308050 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1483793 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1079459 (The Pile)

Max Activating Token Index: 679

Text #10

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.4126. Min Act: -0.0000

Data Index: 340062 (The Pile)

Max Activating Token Index: 780

Text #11

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1194869 (The Pile)

Max Activating Token Index: 876

Text #12

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3639. Min Act: -0.0000

Data Index: 279124 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3668. Min Act: -0.0000

Data Index: 288453 (The Pile)

Max Activating Token Index: 570

Text #14

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3259. Min Act: -0.0000

Data Index: 290777 (The Pile)

Max Activating Token Index: 397

Text #15

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1827119 (The Pile)

Max Activating Token Index: 642

Text #16

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1249710 (The Pile)

Max Activating Token Index: 549

Text #17

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1853630 (The Pile)

Max Activating Token Index: 789

Text #18

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3329. Min Act: -0.0000

Data Index: 271524 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3139. Min Act: -0.0000

Data Index: 271240 (The Pile)

Max Activating Token Index: 474