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

Dataset: The Pile

Neuron 4947 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.8546. Min Act: -0.0000

Data Index: 683263 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7244. Min Act: -0.0000

Data Index: 132002 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1815600 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1736756 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6774. Min Act: -0.0000

Data Index: 686447 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1157156 (The Pile)

Max Activating Token Index: 44

Text #6

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1164691 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1950777 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1596523 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6766. Min Act: -0.0000

Data Index: 190953 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1874074 (The Pile)

Max Activating Token Index: 119

Text #11

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6467. Min Act: -0.0000

Data Index: 456815 (The Pile)

Max Activating Token Index: 36

Text #12

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1105211 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1156410 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1397193 (The Pile)

Max Activating Token Index: 781

Text #15

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6186. Min Act: -0.0000

Data Index: 746444 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1685178 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1823640 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6133. Min Act: -0.0000

Data Index: 599232 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6466. Min Act: -0.0000

Data Index: 206332 (The Pile)

Max Activating Token Index: 466