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

Dataset: The Pile

Neuron 2623 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0912. Min Act: -0.0001

Data Index: 644826 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1638832 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0789. Min Act: -0.0001

Data Index: 240342 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0839. Min Act: -0.0001

Data Index: 461787 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0001

Data Index: 979606 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0743. Min Act: -0.0001

Data Index: 895171 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0780. Min Act: -0.0001

Data Index: 958261 (The Pile)

Max Activating Token Index: 76

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0649. Min Act: -0.0001

Data Index: 733782 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1450512 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0705. Min Act: -0.0001

Data Index: 786827 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1595428 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1941576 (The Pile)

Max Activating Token Index: 970

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0701. Min Act: -0.0001

Data Index: 702575 (The Pile)

Max Activating Token Index: 464

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1340911 (The Pile)

Max Activating Token Index: 911

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1139673 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0760. Min Act: -0.0001

Data Index: 664767 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1958338 (The Pile)

Max Activating Token Index: 825

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0680. Min Act: -0.0000

Data Index: 735345 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1342989 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1735888 (The Pile)

Max Activating Token Index: 402