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

Dataset: The Pile

Neuron 2107 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: 1.4376. Min Range: -1.4376

Max Act: 1.4376. Min Act: -0.0000

Data Index: 1885907 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.0699. Min Act: -0.0000

Data Index: 1190011 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.0669. Min Act: -0.0000

Data Index: 894130 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.0297. Min Act: -0.0000

Data Index: 335297 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.1006. Min Act: -0.0000

Data Index: 71161 (The Pile)

Max Activating Token Index: 634

Text #5

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9456. Min Act: -0.0000

Data Index: 1080174 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.0606. Min Act: -0.0000

Data Index: 289395 (The Pile)

Max Activating Token Index: 972

Text #7

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9937. Min Act: -0.0000

Data Index: 1247118 (The Pile)

Max Activating Token Index: 439

Text #8

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1951054 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.0256. Min Act: -0.0000

Data Index: 738104 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.0303. Min Act: -0.0000

Data Index: 386612 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1788603 (The Pile)

Max Activating Token Index: 830

Text #12

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9362. Min Act: -0.0000

Data Index: 136720 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9255. Min Act: -0.0000

Data Index: 799421 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9597. Min Act: -0.0000

Data Index: 578437 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1820042 (The Pile)

Max Activating Token Index: 234

Text #16

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9641. Min Act: -0.0000

Data Index: 347753 (The Pile)

Max Activating Token Index: 995

Text #17

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.8892. Min Act: -0.0000

Data Index: 539537 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1280723 (The Pile)

Max Activating Token Index: 641

Text #19

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9529. Min Act: -0.0000

Data Index: 417672 (The Pile)

Max Activating Token Index: 709