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

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

Neuron 389 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.8864. Min Act: -0.0001

Data Index: 859357 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.5623. Min Act: -0.0001

Data Index: 1054221 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.3474. Min Act: -0.0001

Data Index: 1025093 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.3343. Min Act: -0.0001

Data Index: 1181081 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.3080. Min Act: -0.0001

Data Index: 75988 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.4185. Min Act: -0.0001

Data Index: 284377 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2602. Min Act: -0.0001

Data Index: 794259 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2286. Min Act: -0.0001

Data Index: 552508 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2792. Min Act: -0.0001

Data Index: 830868 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2724. Min Act: -0.0001

Data Index: 1105162 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2160. Min Act: -0.0001

Data Index: 1022197 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.1861. Min Act: -0.0001

Data Index: 888397 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.1755. Min Act: -0.0001

Data Index: 70552 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.1563. Min Act: -0.0001

Data Index: 813580 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.1798. Min Act: -0.0001

Data Index: 1149915 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2115. Min Act: -0.0001

Data Index: 392867 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2151. Min Act: -0.0001

Data Index: 1212688 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2175. Min Act: -0.0001

Data Index: 210669 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2058. Min Act: -0.0001

Data Index: 1194330 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.1584. Min Act: -0.0001

Data Index: 261620 (C4 (Web Text))

Max Activating Token Index: 1002