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

Dataset: The Pile

Neuron 1751 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: 1.2082. Min Range: -1.2082

Max Act: 1.2082. Min Act: 0.0000

Data Index: 1629904 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.1375. Min Act: -0.0000

Data Index: 462982 (The Pile)

Max Activating Token Index: 75

Text #2

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1877193 (The Pile)

Max Activating Token Index: 27

Text #3

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.0889. Min Act: -0.0000

Data Index: 933518 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.0481. Min Act: -0.0000

Data Index: 836891 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.0652. Min Act: -0.0000

Data Index: 1310026 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.0401. Min Act: -0.0000

Data Index: 1953940 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.0607. Min Act: -0.0000

Data Index: 1688564 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.0548. Min Act: -0.0000

Data Index: 293652 (The Pile)

Max Activating Token Index: 916

Text #9

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1369738 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1630182 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9597. Min Act: -0.0000

Data Index: 806720 (The Pile)

Max Activating Token Index: 77

Text #12

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9849. Min Act: -0.0000

Data Index: 1462411 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1239114 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1100425 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9725. Min Act: -0.0000

Data Index: 176350 (The Pile)

Max Activating Token Index: 649

Text #16

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1905472 (The Pile)

Max Activating Token Index: 35

Text #17

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9690. Min Act: -0.0000

Data Index: 434542 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9379. Min Act: -0.0000

Data Index: 1426021 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9736. Min Act: -0.0000

Data Index: 594586 (The Pile)

Max Activating Token Index: 663