Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 770 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5532. Min Range: -2.5532

Max Act: 2.5532. Min Act: -0.0000

Data Index: 77376 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.9945. Min Act: -0.0000

Data Index: 23382 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.9981. Min Act: -0.0000

Data Index: 1319783 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 2.5532. Min Range: -2.5532

Max Act: 2.0790. Min Act: -0.0000

Data Index: 405354 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.9505. Min Act: -0.0000

Data Index: 181111 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.8693. Min Act: -0.0000

Data Index: 410796 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.7357. Min Act: -0.0000

Data Index: 664170 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.7106. Min Act: -0.0000

Data Index: 956520 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.6828. Min Act: -0.0000

Data Index: 168172 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.6826. Min Act: -0.0000

Data Index: 733756 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.7733. Min Act: -0.0000

Data Index: 1035247 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.4848. Min Act: -0.0000

Data Index: 831346 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.4874. Min Act: -0.0000

Data Index: 1314005 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.6827. Min Act: -0.0000

Data Index: 1188418 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.5594. Min Act: -0.0000

Data Index: 448647 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.5474. Min Act: -0.0000

Data Index: 1070909 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.4884. Min Act: -0.0000

Data Index: 208117 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.3362. Min Act: -0.0000

Data Index: 476614 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.4935. Min Act: -0.0000

Data Index: 1106834 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 2.5532. Min Range: -2.5532

Max Act: 1.5268. Min Act: -0.0000

Data Index: 441332 (C4 (Web Text))

Max Activating Token Index: 731