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

Dataset: The Pile

Neuron 1729 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.7205. Min Act: -0.0000

Data Index: 559950 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1798328 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4609. Min Act: -0.0000

Data Index: 493621 (The Pile)

Max Activating Token Index: 781

Text #3

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5430. Min Act: -0.0000

Data Index: 180934 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1525628 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5029. Min Act: -0.0000

Data Index: 800533 (The Pile)

Max Activating Token Index: 184

Text #6

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5005. Min Act: -0.0000

Data Index: 596062 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1329249 (The Pile)

Max Activating Token Index: 287

Text #8

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4493. Min Act: -0.0000

Data Index: 623835 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4459. Min Act: -0.0000

Data Index: 376493 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1196271 (The Pile)

Max Activating Token Index: 451

Text #11

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1400474 (The Pile)

Max Activating Token Index: 393

Text #12

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1354669 (The Pile)

Max Activating Token Index: 141

Text #13

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4793. Min Act: -0.0000

Data Index: 645120 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1651297 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4289. Min Act: -0.0000

Data Index: 620374 (The Pile)

Max Activating Token Index: 725

Text #16

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4492. Min Act: -0.0000

Data Index: 518090 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4528. Min Act: -0.0000

Data Index: 91845 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4202. Min Act: -0.0000

Data Index: 890788 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4360. Min Act: -0.0000

Data Index: 251968 (The Pile)

Max Activating Token Index: 168