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

Dataset: The Pile

Neuron 1767 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: 0.8692. Min Range: -0.8692

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1603395 (The Pile)

Max Activating Token Index: 717

Text #1

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1879334 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1660319 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1396652 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7313. Min Act: -0.0000

Data Index: 860869 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1945138 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1340542 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1250095 (The Pile)

Max Activating Token Index: 996

Text #8

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6869. Min Act: -0.0000

Data Index: 357628 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1271081 (The Pile)

Max Activating Token Index: 1002

Text #10

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1755715 (The Pile)

Max Activating Token Index: 893

Text #11

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6216. Min Act: -0.0000

Data Index: 752047 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6388. Min Act: -0.0000

Data Index: 566376 (The Pile)

Max Activating Token Index: 736

Text #13

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6559. Min Act: -0.0000

Data Index: 338975 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1168712 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6014. Min Act: -0.0000

Data Index: 854243 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1369289 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6276. Min Act: -0.0000

Data Index: 233575 (The Pile)

Max Activating Token Index: 768

Text #18

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1071247 (The Pile)

Max Activating Token Index: 602

Text #19

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1012967 (The Pile)

Max Activating Token Index: 806