Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 965 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.8725. Min Act: -0.0000

Data Index: 91901 (The Pile)

Max Activating Token Index: 595

Text #1

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1907387 (The Pile)

Max Activating Token Index: 936

Text #2

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6868. Min Act: -0.0000

Data Index: 856056 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6928. Min Act: -0.0000

Data Index: 387275 (The Pile)

Max Activating Token Index: 174

Text #4

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6924. Min Act: -0.0000

Data Index: 878343 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7093. Min Act: -0.0000

Data Index: 467953 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6533. Min Act: -0.0000

Data Index: 506283 (The Pile)

Max Activating Token Index: 170

Text #7

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7193. Min Act: -0.0000

Data Index: 838039 (The Pile)

Max Activating Token Index: 857

Text #8

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1508657 (The Pile)

Max Activating Token Index: 973

Text #9

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6384. Min Act: -0.0000

Data Index: 206509 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1528972 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1167074 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6300. Min Act: -0.0000

Data Index: 72112 (The Pile)

Max Activating Token Index: 656

Text #13

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1350248 (The Pile)

Max Activating Token Index: 118

Text #14

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1401 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1693139 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.5957. Min Act: -0.0000

Data Index: 237627 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1102374 (The Pile)

Max Activating Token Index: 35

Text #18

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1591667 (The Pile)

Max Activating Token Index: 860

Text #19

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1749580 (The Pile)

Max Activating Token Index: 691