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

Dataset: The Pile

Neuron 633 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1102386 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2814. Min Act: -0.0000

Data Index: 449811 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2596. Min Act: -0.0000

Data Index: 774602 (The Pile)

Max Activating Token Index: 260

Text #3

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1637875 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2475. Min Act: -0.0000

Data Index: 85792 (The Pile)

Max Activating Token Index: 727

Text #5

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2181. Min Act: -0.0000

Data Index: 251112 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1321501 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1355190 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1865365 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1525664 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1741978 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2032. Min Act: -0.0000

Data Index: 673686 (The Pile)

Max Activating Token Index: 33

Text #12

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1667252 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2122. Min Act: -0.0000

Data Index: 46148 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1763394 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1987. Min Act: -0.0000

Data Index: 987902 (The Pile)

Max Activating Token Index: 434

Text #16

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1830726 (The Pile)

Max Activating Token Index: 706

Text #17

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1970. Min Act: -0.0000

Data Index: 192874 (The Pile)

Max Activating Token Index: 431

Text #18

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1908010 (The Pile)

Max Activating Token Index: 522

Text #19

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1890. Min Act: -0.0000

Data Index: 78343 (The Pile)

Max Activating Token Index: 44