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

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

Neuron 4318 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.8610. Min Act: -0.0000

Data Index: 429030 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.8273. Min Act: -0.0000

Data Index: 82467 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1249063 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.8181. Min Act: -0.0000

Data Index: 849146 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1335903 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7712. Min Act: -0.0000

Data Index: 846395 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6995. Min Act: -0.0000

Data Index: 336649 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1228248 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1087341 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7274. Min Act: -0.0000

Data Index: 497922 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7672. Min Act: -0.0000

Data Index: 261371 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7694. Min Act: -0.0000

Data Index: 634028 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6566. Min Act: -0.0000

Data Index: 571996 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7191. Min Act: -0.0000

Data Index: 778488 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7138. Min Act: -0.0000

Data Index: 759664 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7309. Min Act: -0.0000

Data Index: 639073 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7081. Min Act: -0.0000

Data Index: 129760 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6829. Min Act: -0.0000

Data Index: 767180 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.6728. Min Act: -0.0000

Data Index: 477844 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.8610. Min Range: -0.8610

Max Act: 0.7147. Min Act: -0.0000

Data Index: 317812 (C4 (Web Text))

Max Activating Token Index: 40