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

Dataset: The Pile

Neuron 2606 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1131652 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.6320. Min Act: -0.0000

Data Index: 835128 (The Pile)

Max Activating Token Index: 471

Text #2

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1027187 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1656474 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1127332 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.5129. Min Act: -0.0000

Data Index: 95542 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1294783 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1351478 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.5199. Min Act: -0.0000

Data Index: 15760 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.5041. Min Act: -0.0000

Data Index: 940892 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1254870 (The Pile)

Max Activating Token Index: 848

Text #11

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1705928 (The Pile)

Max Activating Token Index: 598

Text #12

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1522041 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1556953 (The Pile)

Max Activating Token Index: 856

Text #14

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1235662 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4343. Min Act: -0.0000

Data Index: 955151 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1901679 (The Pile)

Max Activating Token Index: 1008

Text #17

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1802692 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1183424 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4691. Min Act: -0.0000

Data Index: 960282 (The Pile)

Max Activating Token Index: 968