Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3199 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.8077. Min Act: -0.0002

Data Index: 697428 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5745. Min Act: -0.0002

Data Index: 1111356 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5357. Min Act: -0.0002

Data Index: 543711 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5346. Min Act: -0.0003

Data Index: 515799 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5067. Min Act: -0.0003

Data Index: 927328 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4827. Min Act: -0.0002

Data Index: 1263789 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4954. Min Act: -0.0003

Data Index: 292725 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4909. Min Act: -0.0002

Data Index: 118427 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4879. Min Act: -0.0002

Data Index: 692826 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4865. Min Act: -0.0003

Data Index: 1083427 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4729. Min Act: -0.0003

Data Index: 1089905 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4730. Min Act: -0.0003

Data Index: 1277496 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4727. Min Act: -0.0002

Data Index: 1029606 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4716. Min Act: -0.0002

Data Index: 387078 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4561. Min Act: -0.0003

Data Index: 782994 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4334. Min Act: -0.0002

Data Index: 105560 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4467. Min Act: -0.0002

Data Index: 884832 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4610. Min Act: -0.0003

Data Index: 23055 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4586. Min Act: -0.0002

Data Index: 825552 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.4734. Min Act: -0.0003

Data Index: 847842 (C4 (Web Text))

Max Activating Token Index: 412