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

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

Neuron 3757 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: 1.6372. Min Range: -1.6372

Max Act: 1.6372. Min Act: -0.0000

Data Index: 1098670 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.5566. Min Act: -0.0000

Data Index: 882209 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.5412. Min Act: -0.0000

Data Index: 1157315 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.4854. Min Act: -0.0000

Data Index: 949847 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.4634. Min Act: -0.0000

Data Index: 1159526 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.4585. Min Act: -0.0000

Data Index: 1211319 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.3680. Min Act: -0.0000

Data Index: 656391 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.4416. Min Act: -0.0000

Data Index: 195491 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.3519. Min Act: -0.0000

Data Index: 496532 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.4171. Min Act: -0.0000

Data Index: 1013077 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.3157. Min Act: -0.0000

Data Index: 909841 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.4812. Min Act: -0.0000

Data Index: 827867 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.3859. Min Act: -0.0000

Data Index: 373599 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.3525. Min Act: -0.0000

Data Index: 580119 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.3466. Min Act: -0.0000

Data Index: 236347 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1076055 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.2972. Min Act: -0.0000

Data Index: 111069 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.2619. Min Act: -0.0000

Data Index: 521820 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.2959. Min Act: -0.0000

Data Index: 1064528 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 1.6372. Min Range: -1.6372

Max Act: 1.3283. Min Act: -0.0000

Data Index: 1303735 (C4 (Web Text))

Max Activating Token Index: 491