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

Dataset: The Pile

Neuron 2791 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1769846 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1674292 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1885. Min Act: -0.0000

Data Index: 321937 (The Pile)

Max Activating Token Index: 581

Text #3

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1104343 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1187318 (The Pile)

Max Activating Token Index: 870

Text #5

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1955. Min Act: -0.0000

Data Index: 813489 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1526. Min Act: -0.0000

Data Index: 43745 (The Pile)

Max Activating Token Index: 185

Text #7

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1625. Min Act: -0.0000

Data Index: 249869 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1313602 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1465741 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1652. Min Act: -0.0000

Data Index: 1443842 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1973120 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1808550 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1615. Min Act: -0.0000

Data Index: 700701 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1450. Min Act: -0.0000

Data Index: 36080 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1554. Min Act: -0.0000

Data Index: 531575 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1731. Min Act: -0.0000

Data Index: 878843 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1187386 (The Pile)

Max Activating Token Index: 879

Text #18

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1200636 (The Pile)

Max Activating Token Index: 910

Text #19

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1540. Min Act: -0.0000

Data Index: 417940 (The Pile)

Max Activating Token Index: 632