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

Dataset: The Pile

Neuron 2415 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: 3.0093. Min Range: -3.0093

Max Act: 3.0093. Min Act: -0.0000

Data Index: 1860799 (The Pile)

Max Activating Token Index: 412

Text #1

Max Range: 3.0093. Min Range: -3.0093

Max Act: 2.2868. Min Act: -0.0000

Data Index: 167289 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 3.0093. Min Range: -3.0093

Max Act: 2.0856. Min Act: -0.0000

Data Index: 202650 (The Pile)

Max Activating Token Index: 858

Text #3

Max Range: 3.0093. Min Range: -3.0093

Max Act: 2.0435. Min Act: -0.0000

Data Index: 629156 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.9852. Min Act: -0.0000

Data Index: 292294 (The Pile)

Max Activating Token Index: 649

Text #5

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.9436. Min Act: -0.0000

Data Index: 688819 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 3.0093. Min Range: -3.0093

Max Act: 2.0222. Min Act: -0.0000

Data Index: 814219 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.8693. Min Act: -0.0000

Data Index: 937691 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.9145. Min Act: -0.0000

Data Index: 1068790 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 3.0093. Min Range: -3.0093

Max Act: 2.1307. Min Act: -0.0000

Data Index: 414727 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.8782. Min Act: -0.0000

Data Index: 157086 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.8348. Min Act: -0.0000

Data Index: 451297 (The Pile)

Max Activating Token Index: 942

Text #12

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.8538. Min Act: -0.0000

Data Index: 786174 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.4663. Min Act: -0.0000

Data Index: 399489 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.8875. Min Act: -0.0000

Data Index: 378219 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.8688. Min Act: -0.0000

Data Index: 664915 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.7652. Min Act: -0.0000

Data Index: 949507 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.7632. Min Act: -0.0000

Data Index: 1057441 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.5772. Min Act: -0.0000

Data Index: 151846 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 3.0093. Min Range: -3.0093

Max Act: 1.7628. Min Act: -0.0000

Data Index: 1492855 (The Pile)

Max Activating Token Index: 660