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

Dataset: The Pile

Neuron 1963 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1049685 (The Pile)

Max Activating Token Index: 713

Text #1

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1547051 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.7027. Min Act: -0.0000

Data Index: 636635 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1233429 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1251548 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.6085. Min Act: -0.0000

Data Index: 755718 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.6137. Min Act: 0.0000

Data Index: 1863110 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1040566 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5967. Min Act: -0.0000

Data Index: 853901 (The Pile)

Max Activating Token Index: 916

Text #9

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1253786 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5609. Min Act: 0.0000

Data Index: 1759666 (The Pile)

Max Activating Token Index: 371

Text #11

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1338008 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1332936 (The Pile)

Max Activating Token Index: 1013

Text #13

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5029. Min Act: -0.0000

Data Index: 438869 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5057. Min Act: -0.0000

Data Index: 729180 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5363. Min Act: 0.0000

Data Index: 871687 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5558. Min Act: -0.0000

Data Index: 218502 (The Pile)

Max Activating Token Index: 691

Text #17

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1373653 (The Pile)

Max Activating Token Index: 591

Text #18

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5285. Min Act: 0.0000

Data Index: 340277 (The Pile)

Max Activating Token Index: 706

Text #19

Max Range: 0.7208. Min Range: -0.7208

Max Act: 0.5858. Min Act: 0.0001

Data Index: 1710027 (The Pile)

Max Activating Token Index: 111