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

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

Neuron 4033 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4391. Min Range: -2.4391

Max Act: 2.4391. Min Act: -0.0000

Data Index: 489240 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 2.4391. Min Range: -2.4391

Max Act: 2.2902. Min Act: -0.0000

Data Index: 255390 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 2.4391. Min Range: -2.4391

Max Act: 2.2645. Min Act: -0.0000

Data Index: 762194 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 2.4391. Min Range: -2.4391

Max Act: 2.3017. Min Act: -0.0000

Data Index: 141327 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 2.4391. Min Range: -2.4391

Max Act: 2.0122. Min Act: -0.0000

Data Index: 1035826 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 2.4391. Min Range: -2.4391

Max Act: 2.3128. Min Act: -0.0000

Data Index: 204808 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 2.4391. Min Range: -2.4391

Max Act: 2.1367. Min Act: -0.0000

Data Index: 886619 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.9884. Min Act: -0.0000

Data Index: 1125087 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.8621. Min Act: -0.0000

Data Index: 1352263 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.8814. Min Act: -0.0000

Data Index: 400291 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.9407. Min Act: -0.0000

Data Index: 396926 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.9300. Min Act: -0.0000

Data Index: 327904 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.9180. Min Act: -0.0000

Data Index: 6830 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 2.4391. Min Range: -2.4391

Max Act: 2.1228. Min Act: -0.0000

Data Index: 1125461 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.8668. Min Act: -0.0000

Data Index: 150297 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.7481. Min Act: -0.0000

Data Index: 582542 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.9278. Min Act: -0.0000

Data Index: 771472 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.9175. Min Act: -0.0000

Data Index: 1239096 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.6958. Min Act: -0.0000

Data Index: 1614174 (Python Code)

Max Activating Token Index: 368

Text #19

Max Range: 2.4391. Min Range: -2.4391

Max Act: 1.7689. Min Act: -0.0000

Data Index: 586492 (C4 (Web Text))

Max Activating Token Index: 286