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

Dataset: The Pile

Neuron 3836 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.6106. Min Act: -0.0000

Data Index: 1679248 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1060296 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.1606. Min Act: -0.0000

Data Index: 86208 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.2192. Min Act: -0.0000

Data Index: 519770 (The Pile)

Max Activating Token Index: 268

Text #4

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.1590. Min Act: -0.0000

Data Index: 786818 (The Pile)

Max Activating Token Index: 36

Text #5

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.1222. Min Act: -0.0000

Data Index: 533490 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 1.6106. Min Range: -1.6106

Max Act: 0.9830. Min Act: -0.0000

Data Index: 908321 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0723. Min Act: -0.0000

Data Index: 1054515 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0087. Min Act: -0.0000

Data Index: 977001 (The Pile)

Max Activating Token Index: 950

Text #9

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0119. Min Act: -0.0000

Data Index: 1960857 (The Pile)

Max Activating Token Index: 351

Text #10

Max Range: 1.6106. Min Range: -1.6106

Max Act: 0.9380. Min Act: -0.0000

Data Index: 819011 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0249. Min Act: -0.0000

Data Index: 856800 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0236. Min Act: -0.0000

Data Index: 1356037 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.1073. Min Act: -0.0000

Data Index: 642192 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1267240 (The Pile)

Max Activating Token Index: 591

Text #15

Max Range: 1.6106. Min Range: -1.6106

Max Act: 0.9556. Min Act: -0.0000

Data Index: 113755 (The Pile)

Max Activating Token Index: 289

Text #16

Max Range: 1.6106. Min Range: -1.6106

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1988133 (The Pile)

Max Activating Token Index: 895

Text #17

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1508792 (The Pile)

Max Activating Token Index: 770

Text #18

Max Range: 1.6106. Min Range: -1.6106

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1607806 (The Pile)

Max Activating Token Index: 120

Text #19

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1801122 (The Pile)

Max Activating Token Index: 148