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

Dataset: The Pile

Neuron 1165 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: 0.9887. Min Range: -0.9887

Max Act: 0.9887. Min Act: -0.0000

Data Index: 754517 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.9819. Min Act: -0.0000

Data Index: 1324315 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.9818. Min Act: -0.0000

Data Index: 461459 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1763667 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.9674. Min Act: -0.0000

Data Index: 673518 (The Pile)

Max Activating Token Index: 627

Text #5

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.9311. Min Act: -0.0000

Data Index: 323798 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1755372 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8177. Min Act: -0.0000

Data Index: 665570 (The Pile)

Max Activating Token Index: 351

Text #8

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8540. Min Act: -0.0000

Data Index: 595019 (The Pile)

Max Activating Token Index: 755

Text #9

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8293. Min Act: -0.0000

Data Index: 1561117 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8430. Min Act: -0.0000

Data Index: 723535 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1824240 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1385982 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7932. Min Act: -0.0000

Data Index: 818044 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7881. Min Act: -0.0000

Data Index: 951980 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8474. Min Act: -0.0000

Data Index: 751372 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1829772 (The Pile)

Max Activating Token Index: 518

Text #17

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1766269 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1517997 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1031005 (The Pile)

Max Activating Token Index: 716