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

Dataset: The Pile

Neuron 3686 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1180153 (The Pile)

Max Activating Token Index: 620

Text #1

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1388105 (The Pile)

Max Activating Token Index: 542

Text #2

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1862961 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1518788 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1315799 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1110290 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1291795 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1586099 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1006665 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1511430 (The Pile)

Max Activating Token Index: 930

Text #10

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1448839 (The Pile)

Max Activating Token Index: 438

Text #11

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3394. Min Act: -0.0000

Data Index: 925570 (The Pile)

Max Activating Token Index: 282

Text #12

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1704262 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1510123 (The Pile)

Max Activating Token Index: 747

Text #14

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3221. Min Act: -0.0000

Data Index: 584383 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1793772 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1014337 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3079. Min Act: -0.0000

Data Index: 732790 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1402414 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1641057 (The Pile)

Max Activating Token Index: 247