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

Dataset: The Pile

Neuron 4849 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: 1.7866. Min Range: -1.7866

Max Act: 1.7866. Min Act: -0.0000

Data Index: 458408 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 1.7866. Min Range: -1.7866

Max Act: 1.1098. Min Act: -0.0000

Data Index: 210776 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1828215 (The Pile)

Max Activating Token Index: 741

Text #3

Max Range: 1.7866. Min Range: -1.7866

Max Act: 1.0573. Min Act: -0.0000

Data Index: 374888 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1408922 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9194. Min Act: -0.0000

Data Index: 771998 (The Pile)

Max Activating Token Index: 320

Text #6

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9355. Min Act: -0.0000

Data Index: 583772 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1853285 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9062. Min Act: -0.0000

Data Index: 893425 (The Pile)

Max Activating Token Index: 898

Text #9

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1252390 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1378564 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8553. Min Act: -0.0000

Data Index: 629970 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9187. Min Act: -0.0000

Data Index: 422121 (The Pile)

Max Activating Token Index: 350

Text #13

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1720364 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9058. Min Act: -0.0000

Data Index: 19044 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 1.7866. Min Range: -1.7866

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1500907 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8503. Min Act: -0.0000

Data Index: 788198 (The Pile)

Max Activating Token Index: 399

Text #17

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1640892 (The Pile)

Max Activating Token Index: 421

Text #18

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1338904 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8997. Min Act: -0.0000

Data Index: 582028 (The Pile)

Max Activating Token Index: 979