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

Dataset: The Pile

Neuron 3115 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: 0.9676. Min Range: -0.9676

Max Act: 0.9676. Min Act: -0.0000

Data Index: 106695 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8854. Min Act: -0.0000

Data Index: 256404 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1213175 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8889. Min Act: -0.0000

Data Index: 352587 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8344. Min Act: 0.0000

Data Index: 1464898 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1446001 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7789. Min Act: 0.0000

Data Index: 1935226 (The Pile)

Max Activating Token Index: 175

Text #7

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1679705 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8388. Min Act: -0.0000

Data Index: 396877 (The Pile)

Max Activating Token Index: 362

Text #9

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1859185 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7782. Min Act: -0.0000

Data Index: 477100 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8053. Min Act: -0.0000

Data Index: 997791 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1303393 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1934044 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8026. Min Act: -0.0000

Data Index: 984111 (The Pile)

Max Activating Token Index: 95

Text #15

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1657869 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1586786 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7794. Min Act: -0.0000

Data Index: 293775 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1643964 (The Pile)

Max Activating Token Index: 805

Text #19

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1733636 (The Pile)

Max Activating Token Index: 470