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

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

Neuron 1418 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: 1.4745. Min Range: -1.4745

Max Act: 1.4745. Min Act: -0.0000

Data Index: 967233 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.4745. Min Range: -1.4745

Max Act: 1.4711. Min Act: -0.0000

Data Index: 512220 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 1.4745. Min Range: -1.4745

Max Act: 1.2614. Min Act: -0.0000

Data Index: 592554 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1140764 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 1.4745. Min Range: -1.4745

Max Act: 1.1831. Min Act: -0.0000

Data Index: 162905 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 1.4745. Min Range: -1.4745

Max Act: 1.0213. Min Act: -0.0000

Data Index: 1343558 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 1.4745. Min Range: -1.4745

Max Act: 1.0093. Min Act: -0.0000

Data Index: 41445 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.8568. Min Act: -0.0000

Data Index: 115662 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1124974 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 1.4745. Min Range: -1.4745

Max Act: 1.0372. Min Act: -0.0000

Data Index: 16039 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.9552. Min Act: -0.0000

Data Index: 797078 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.9556. Min Act: -0.0000

Data Index: 808316 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.9235. Min Act: -0.0000

Data Index: 634406 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.9810. Min Act: -0.0000

Data Index: 326058 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.9818. Min Act: -0.0000

Data Index: 932014 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1348150 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.9035. Min Act: -0.0000

Data Index: 493178 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.9085. Min Act: -0.0000

Data Index: 5025 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.9111. Min Act: -0.0000

Data Index: 764462 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 1.4745. Min Range: -1.4745

Max Act: 0.9307. Min Act: -0.0000

Data Index: 477850 (C4 (Web Text))

Max Activating Token Index: 577