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

Dataset: The Pile

Neuron 3255 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.6558. Min Act: -0.0000

Data Index: 410133 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.7232. Min Act: -0.0000

Data Index: 1676674 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.5704. Min Act: -0.0000

Data Index: 512186 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.6097. Min Act: -0.0000

Data Index: 791266 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.5772. Min Act: -0.0000

Data Index: 1151938 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.6194. Min Act: -0.0000

Data Index: 1205784 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.6326. Min Act: -0.0000

Data Index: 1451267 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.4834. Min Act: -0.0000

Data Index: 637822 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.4525. Min Act: -0.0000

Data Index: 1101011 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.5642. Min Act: -0.0000

Data Index: 172005 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.5948. Min Act: -0.0000

Data Index: 1554483 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.5370. Min Act: -0.0000

Data Index: 427314 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1308709 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.5305. Min Act: -0.0000

Data Index: 7013 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.4453. Min Act: -0.0000

Data Index: 1380435 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.4248. Min Act: -0.0000

Data Index: 1407714 (The Pile)

Max Activating Token Index: 246

Text #16

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.4827. Min Act: -0.0000

Data Index: 1546222 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.4684. Min Act: -0.0000

Data Index: 454100 (The Pile)

Max Activating Token Index: 46

Text #18

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.4110. Min Act: -0.0000

Data Index: 1967246 (The Pile)

Max Activating Token Index: 757

Text #19

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.5377. Min Act: -0.0000

Data Index: 339659 (The Pile)

Max Activating Token Index: 726