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

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

Neuron 463 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.7836. Min Act: -0.0000

Data Index: 274979 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.5166. Min Act: -0.0000

Data Index: 1018411 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.5081. Min Act: -0.0000

Data Index: 763148 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.4687. Min Act: -0.0000

Data Index: 1259865 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1170730 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.5464. Min Act: -0.0000

Data Index: 1299651 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.5261. Min Act: -0.0000

Data Index: 796521 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.6196. Min Act: -0.0000

Data Index: 216123 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.5305. Min Act: -0.0000

Data Index: 796802 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.4483. Min Act: -0.0000

Data Index: 143946 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.4294. Min Act: -0.0000

Data Index: 314997 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.4000. Min Act: -0.0000

Data Index: 992040 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.5298. Min Act: -0.0000

Data Index: 1304343 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.3581. Min Act: -0.0000

Data Index: 1276269 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.3555. Min Act: -0.0000

Data Index: 540740 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.4179. Min Act: -0.0000

Data Index: 866953 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.3817. Min Act: -0.0000

Data Index: 1279108 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.1983. Min Act: -0.0000

Data Index: 1117951 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.3780. Min Act: -0.0000

Data Index: 530496 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 1.7836. Min Range: -1.7836

Max Act: 1.3634. Min Act: -0.0000

Data Index: 730475 (C4 (Web Text))

Max Activating Token Index: 877