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

Dataset: The Pile

Neuron 254 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1298. Min Range: -1.1298

Max Act: 1.1298. Min Act: -0.0000

Data Index: 1931413 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 1.1298. Min Range: -1.1298

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1002285 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 1.1298. Min Range: -1.1298

Max Act: 1.0665. Min Act: -0.0000

Data Index: 1893666 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 1.1298. Min Range: -1.1298

Max Act: 1.0111. Min Act: -0.0000

Data Index: 968405 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9248. Min Act: -0.0000

Data Index: 28194 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9733. Min Act: -0.0000

Data Index: 131307 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1837964 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9055. Min Act: -0.0000

Data Index: 660381 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1891103 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.8669. Min Act: -0.0000

Data Index: 447844 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1681978 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.8109. Min Act: -0.0000

Data Index: 355047 (The Pile)

Max Activating Token Index: 531

Text #12

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.7599. Min Act: -0.0000

Data Index: 967988 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.7350. Min Act: -0.0000

Data Index: 678209 (The Pile)

Max Activating Token Index: 763

Text #14

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1463150 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1638298 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1816687 (The Pile)

Max Activating Token Index: 194

Text #17

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.8346. Min Act: -0.0000

Data Index: 106334 (The Pile)

Max Activating Token Index: 529

Text #18

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.7610. Min Act: -0.0000

Data Index: 948873 (The Pile)

Max Activating Token Index: 972

Text #19

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.7721. Min Act: -0.0000

Data Index: 677699 (The Pile)

Max Activating Token Index: 52