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

Dataset: The Pile

Neuron 3280 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.7619. Min Act: -0.0000

Data Index: 35493 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1329409 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1146991 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5961. Min Act: -0.0000

Data Index: 697784 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1907314 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5436. Min Act: -0.0000

Data Index: 758041 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1011716 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5163. Min Act: -0.0000

Data Index: 74598 (The Pile)

Max Activating Token Index: 554

Text #8

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1492288 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1583654 (The Pile)

Max Activating Token Index: 428

Text #10

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.4889. Min Act: -0.0000

Data Index: 182039 (The Pile)

Max Activating Token Index: 246

Text #11

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1009400 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5238. Min Act: 0.0000

Data Index: 870867 (The Pile)

Max Activating Token Index: 10

Text #13

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5671. Min Act: -0.0000

Data Index: 518533 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5064. Min Act: -0.0000

Data Index: 954850 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1956506 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1297094 (The Pile)

Max Activating Token Index: 460

Text #17

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1471327 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5276. Min Act: -0.0000

Data Index: 166123 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1422178 (The Pile)

Max Activating Token Index: 906