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

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

Neuron 100 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.7822. Min Act: -0.0001

Data Index: 315972 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.7219. Min Act: -0.0001

Data Index: 101726 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.6932. Min Act: -0.0001

Data Index: 1143302 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.6731. Min Act: -0.0001

Data Index: 644970 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5919. Min Act: -0.0001

Data Index: 976330 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.6093. Min Act: -0.0001

Data Index: 1247480 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5367. Min Act: -0.0001

Data Index: 695975 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.6216. Min Act: -0.0001

Data Index: 1306740 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5508. Min Act: -0.0001

Data Index: 15901 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5642. Min Act: -0.0001

Data Index: 1015669 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5608. Min Act: -0.0001

Data Index: 303259 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5863. Min Act: -0.0001

Data Index: 772115 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5809. Min Act: -0.0001

Data Index: 779725 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5619. Min Act: -0.0001

Data Index: 1081360 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5070. Min Act: -0.0001

Data Index: 618793 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5209. Min Act: -0.0001

Data Index: 1251220 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5570. Min Act: -0.0001

Data Index: 669816 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5513. Min Act: -0.0001

Data Index: 17815 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.4488. Min Act: -0.0001

Data Index: 372975 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.4781. Min Act: -0.0001

Data Index: 14983 (C4 (Web Text))

Max Activating Token Index: 799