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

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

Neuron 3000 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.7778. Min Act: -0.0000

Data Index: 1212040 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.7812. Min Act: -0.0001

Data Index: 1151743 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.5581. Min Act: -0.0001

Data Index: 1234987 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.3370. Min Act: -0.0000

Data Index: 64207 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.3575. Min Act: -0.0000

Data Index: 62080 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.4020. Min Act: -0.0001

Data Index: 260693 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.3527. Min Act: -0.0001

Data Index: 813903 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.3121. Min Act: -0.0000

Data Index: 38973 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.3848. Min Act: -0.0001

Data Index: 1289985 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.2590. Min Act: -0.0000

Data Index: 928959 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.2977. Min Act: -0.0001

Data Index: 5604 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.2411. Min Act: -0.0000

Data Index: 1230418 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.3052. Min Act: -0.0001

Data Index: 1074988 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.1968. Min Act: -0.0001

Data Index: 1004282 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.2925. Min Act: -0.0000

Data Index: 973254 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.2854. Min Act: -0.0001

Data Index: 1306237 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.3248. Min Act: -0.0000

Data Index: 724685 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.1977. Min Act: -0.0001

Data Index: 648243 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.2244. Min Act: -0.0000

Data Index: 474469 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 1.7812. Min Range: -1.7812

Max Act: 1.2607. Min Act: -0.0001

Data Index: 946796 (C4 (Web Text))

Max Activating Token Index: 421