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

Dataset: The Pile

Neuron 793 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: 5.2301. Min Range: -5.2301

Max Act: 5.2301. Min Act: -0.0000

Data Index: 1276532 (The Pile)

Max Activating Token Index: 697

Text #1

Max Range: 5.2301. Min Range: -5.2301

Max Act: 4.9485. Min Act: -0.0000

Data Index: 1363177 (The Pile)

Max Activating Token Index: 731

Text #2

Max Range: 5.2301. Min Range: -5.2301

Max Act: 4.9228. Min Act: -0.0000

Data Index: 328790 (The Pile)

Max Activating Token Index: 595

Text #3

Max Range: 5.2301. Min Range: -5.2301

Max Act: 4.7509. Min Act: -0.0000

Data Index: 1400504 (The Pile)

Max Activating Token Index: 145

Text #4

Max Range: 5.2301. Min Range: -5.2301

Max Act: 4.5464. Min Act: -0.0000

Data Index: 195983 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 5.2301. Min Range: -5.2301

Max Act: 4.0996. Min Act: -0.0000

Data Index: 1786473 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 5.2301. Min Range: -5.2301

Max Act: 4.0841. Min Act: -0.0000

Data Index: 1618478 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 5.2301. Min Range: -5.2301

Max Act: 4.1740. Min Act: -0.0000

Data Index: 595037 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.7267. Min Act: -0.0000

Data Index: 1237451 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.7816. Min Act: -0.0000

Data Index: 1640999 (The Pile)

Max Activating Token Index: 619

Text #10

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.8297. Min Act: -0.0000

Data Index: 418249 (The Pile)

Max Activating Token Index: 368

Text #11

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.5346. Min Act: -0.0000

Data Index: 1044660 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.8176. Min Act: -0.0000

Data Index: 31764 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.8133. Min Act: -0.0000

Data Index: 667515 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.0672. Min Act: -0.0000

Data Index: 321716 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.2574. Min Act: -0.0000

Data Index: 1656081 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.4708. Min Act: -0.0000

Data Index: 58943 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.5454. Min Act: -0.0000

Data Index: 765639 (The Pile)

Max Activating Token Index: 167

Text #18

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.0648. Min Act: -0.0000

Data Index: 1755374 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 5.2301. Min Range: -5.2301

Max Act: 3.4570. Min Act: -0.0000

Data Index: 1982797 (The Pile)

Max Activating Token Index: 819