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

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

Neuron 4830 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7256. Min Range: -7.7256

Max Act: 7.7256. Min Act: -0.0000

Data Index: 721967 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 7.7256. Min Range: -7.7256

Max Act: 6.1189. Min Act: -0.0000

Data Index: 604330 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 7.7256. Min Range: -7.7256

Max Act: 6.0684. Min Act: -0.0000

Data Index: 911133 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 7.7256. Min Range: -7.7256

Max Act: 5.7096. Min Act: -0.0000

Data Index: 1173890 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 7.7256. Min Range: -7.7256

Max Act: 5.8499. Min Act: -0.0000

Data Index: 320914 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 7.7256. Min Range: -7.7256

Max Act: 5.0687. Min Act: -0.0000

Data Index: 1193290 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 7.7256. Min Range: -7.7256

Max Act: 5.2989. Min Act: -0.0000

Data Index: 1094808 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 7.7256. Min Range: -7.7256

Max Act: 5.0076. Min Act: -0.0000

Data Index: 377650 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 7.7256. Min Range: -7.7256

Max Act: 4.8081. Min Act: -0.0000

Data Index: 178711 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 7.7256. Min Range: -7.7256

Max Act: 5.1204. Min Act: -0.0000

Data Index: 1063730 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 7.7256. Min Range: -7.7256

Max Act: 4.7510. Min Act: -0.0000

Data Index: 687442 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 7.7256. Min Range: -7.7256

Max Act: 4.4991. Min Act: -0.0000

Data Index: 772782 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 7.7256. Min Range: -7.7256

Max Act: 5.0356. Min Act: -0.0000

Data Index: 1025591 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 7.7256. Min Range: -7.7256

Max Act: 4.5952. Min Act: -0.0000

Data Index: 391762 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 7.7256. Min Range: -7.7256

Max Act: 4.5528. Min Act: -0.0000

Data Index: 1295371 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 7.7256. Min Range: -7.7256

Max Act: 4.2802. Min Act: -0.0000

Data Index: 1116650 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 7.7256. Min Range: -7.7256

Max Act: 3.9544. Min Act: -0.0000

Data Index: 225617 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 7.7256. Min Range: -7.7256

Max Act: 4.4692. Min Act: -0.0000

Data Index: 667499 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 7.7256. Min Range: -7.7256

Max Act: 4.2484. Min Act: -0.0000

Data Index: 1099426 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 7.7256. Min Range: -7.7256

Max Act: 4.1784. Min Act: -0.0000

Data Index: 502767 (C4 (Web Text))

Max Activating Token Index: 616