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

Dataset: The Pile

Neuron 3288 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: 0.9231. Min Range: -0.9231

Max Act: 0.9231. Min Act: -0.0000

Data Index: 1525950 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1992710 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1948466 (The Pile)

Max Activating Token Index: 614

Text #3

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1152684 (The Pile)

Max Activating Token Index: 350

Text #4

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7040. Min Act: -0.0000

Data Index: 956817 (The Pile)

Max Activating Token Index: 586

Text #5

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7207. Min Act: -0.0000

Data Index: 257954 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7774. Min Act: -0.0000

Data Index: 861421 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1379048 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1219906 (The Pile)

Max Activating Token Index: 54

Text #9

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1000024 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6710. Min Act: -0.0000

Data Index: 586027 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1282543 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.5448. Min Act: -0.0000

Data Index: 313632 (The Pile)

Max Activating Token Index: 821

Text #13

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1931126 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6254. Min Act: -0.0000

Data Index: 754159 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6203. Min Act: -0.0000

Data Index: 985122 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6222. Min Act: -0.0000

Data Index: 746018 (The Pile)

Max Activating Token Index: 884

Text #17

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6511. Min Act: -0.0000

Data Index: 711023 (The Pile)

Max Activating Token Index: 122

Text #18

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.5685. Min Act: -0.0000

Data Index: 954922 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1833489 (The Pile)

Max Activating Token Index: 759