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

Dataset: The Pile

Neuron 2089 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: 0.8430. Min Range: -0.8430

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1842436 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6324. Min Act: -0.0000

Data Index: 408955 (The Pile)

Max Activating Token Index: 154

Text #2

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6406. Min Act: -0.0000

Data Index: 313076 (The Pile)

Max Activating Token Index: 721

Text #3

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5680. Min Act: -0.0000

Data Index: 759716 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5787. Min Act: -0.0000

Data Index: 674067 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4996. Min Act: -0.0000

Data Index: 676136 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5353. Min Act: -0.0000

Data Index: 100843 (The Pile)

Max Activating Token Index: 527

Text #7

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1689231 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5032. Min Act: -0.0000

Data Index: 235172 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1361530 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5080. Min Act: -0.0000

Data Index: 492552 (The Pile)

Max Activating Token Index: 915

Text #11

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1987925 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5077. Min Act: -0.0000

Data Index: 994719 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1749344 (The Pile)

Max Activating Token Index: 942

Text #14

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1838753 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1960583 (The Pile)

Max Activating Token Index: 800

Text #16

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4419. Min Act: -0.0000

Data Index: 942344 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1854180 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4868. Min Act: -0.0000

Data Index: 994690 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1635216 (The Pile)

Max Activating Token Index: 725