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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3070 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.4841. Min Act: -0.0000

Data Index: 858576 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.2306. Min Act: -0.0000

Data Index: 924127 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1322. Min Act: -0.0000

Data Index: 643474 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1167. Min Act: -0.0000

Data Index: 406860 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1643 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1297. Min Act: -0.0000

Data Index: 786238 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1189421 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1512. Min Act: -0.0000

Data Index: 527880 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1279927 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1353. Min Act: -0.0000

Data Index: 351739 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1091842 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1348206 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.1092. Min Act: -0.0000

Data Index: 580387 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0948. Min Act: -0.0000

Data Index: 493849 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0306. Min Act: -0.0000

Data Index: 106244 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0281. Min Act: -0.0000

Data Index: 504772 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.9529. Min Act: -0.0000

Data Index: 800937 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0215. Min Act: -0.0000

Data Index: 911750 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.4841. Min Range: -1.4841

Max Act: 0.9893. Min Act: -0.0000

Data Index: 1093314 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.4841. Min Range: -1.4841

Max Act: 1.0381. Min Act: -0.0000

Data Index: 515054 (C4 (Web Text))

Max Activating Token Index: 929