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

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

Neuron 3769 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.8460. Min Act: -0.0000

Data Index: 565475 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.6808. Min Act: -0.0000

Data Index: 433865 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.1186. Min Act: -0.0000

Data Index: 892510 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.6365. Min Act: -0.0000

Data Index: 77015 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.6114. Min Act: -0.0000

Data Index: 912324 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.7512. Min Act: -0.0000

Data Index: 1297355 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.7438. Min Act: -0.0000

Data Index: 1185004 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.6845. Min Act: -0.0000

Data Index: 1103590 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.6684. Min Act: -0.0000

Data Index: 235105 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.4745. Min Act: -0.0000

Data Index: 866802 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.4038. Min Act: -0.0000

Data Index: 1092725 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.4036. Min Act: -0.0000

Data Index: 1295560 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.5145. Min Act: -0.0000

Data Index: 579993 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.4723. Min Act: -0.0000

Data Index: 164326 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.4705. Min Act: -0.0000

Data Index: 809464 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.4077. Min Act: -0.0000

Data Index: 1171188 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.4077. Min Act: -0.0000

Data Index: 56780 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.4077. Min Act: -0.0000

Data Index: 1068847 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.4077. Min Act: -0.0000

Data Index: 844880 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 4.8460. Min Range: -4.8460

Max Act: 3.1838. Min Act: -0.0000

Data Index: 37925 (C4 (Web Text))

Max Activating Token Index: 205