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

Dataset: The Pile

Neuron 3374 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: 1.2582. Min Range: -1.2582

Max Act: 1.2582. Min Act: -0.0000

Data Index: 827701 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.0977. Min Act: -0.0000

Data Index: 593749 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.0171. Min Act: -0.0000

Data Index: 775223 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9972. Min Act: -0.0000

Data Index: 802868 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9700. Min Act: -0.0000

Data Index: 249954 (The Pile)

Max Activating Token Index: 653

Text #5

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.0562. Min Act: -0.0000

Data Index: 1163597 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.0001. Min Act: -0.0000

Data Index: 1563969 (The Pile)

Max Activating Token Index: 43

Text #7

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1898316 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1967310 (The Pile)

Max Activating Token Index: 533

Text #9

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1121365 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9481. Min Act: -0.0000

Data Index: 756704 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1342738 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8827. Min Act: -0.0000

Data Index: 468257 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1736671 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1113914 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1245195 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1950128 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8882. Min Act: -0.0000

Data Index: 209514 (The Pile)

Max Activating Token Index: 1017

Text #18

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8458. Min Act: -0.0000

Data Index: 581840 (The Pile)

Max Activating Token Index: 919

Text #19

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8989. Min Act: -0.0000

Data Index: 280614 (The Pile)

Max Activating Token Index: 281