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

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

Neuron 3093 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.5398. Min Act: -0.0000

Data Index: 142614 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.5368. Min Act: -0.0000

Data Index: 192051 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1172875 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4858. Min Act: -0.0000

Data Index: 507001 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4246. Min Act: -0.0000

Data Index: 968074 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4711. Min Act: -0.0000

Data Index: 939188 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1006121 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.4325. Min Act: -0.0000

Data Index: 310740 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1122998 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3750. Min Act: -0.0000

Data Index: 39371 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1011367 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3804. Min Act: -0.0000

Data Index: 272914 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1101379 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3712. Min Act: -0.0000

Data Index: 579952 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3805. Min Act: -0.0000

Data Index: 234240 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3865. Min Act: -0.0000

Data Index: 273333 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3504. Min Act: -0.0000

Data Index: 493144 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1322740 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3522. Min Act: -0.0000

Data Index: 805536 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.5398. Min Range: -0.5398

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1516667 (Python Code)

Max Activating Token Index: 481