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

Dataset: The Pile

Neuron 4482 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1759613 (The Pile)

Max Activating Token Index: 847

Text #1

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1510881 (The Pile)

Max Activating Token Index: 549

Text #2

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1397292 (The Pile)

Max Activating Token Index: 337

Text #3

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3751. Min Act: -0.0000

Data Index: 550559 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1018518 (The Pile)

Max Activating Token Index: 859

Text #5

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1232721 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1861585 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3215. Min Act: -0.0000

Data Index: 253174 (The Pile)

Max Activating Token Index: 798

Text #8

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1401290 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3746. Min Act: -0.0000

Data Index: 419542 (The Pile)

Max Activating Token Index: 764

Text #10

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2863. Min Act: -0.0000

Data Index: 476665 (The Pile)

Max Activating Token Index: 1018

Text #11

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1612037 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1443918 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3142. Min Act: -0.0000

Data Index: 190522 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1312522 (The Pile)

Max Activating Token Index: 657

Text #15

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1137597 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1430803 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1488765 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3102. Min Act: -0.0000

Data Index: 167579 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1990146 (The Pile)

Max Activating Token Index: 878