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

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

Neuron 2762 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.6189. Min Act: -0.0002

Data Index: 1626475 (Python Code)

Max Activating Token Index: 856

Text #1

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5688. Min Act: -0.0002

Data Index: 1444613 (Python Code)

Max Activating Token Index: 591

Text #2

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5712. Min Act: -0.0002

Data Index: 1606242 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5718. Min Act: -0.0002

Data Index: 1376207 (Python Code)

Max Activating Token Index: 92

Text #4

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5457. Min Act: -0.0002

Data Index: 1496760 (Python Code)

Max Activating Token Index: 956

Text #5

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5433. Min Act: -0.0002

Data Index: 1479474 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5329. Min Act: -0.0002

Data Index: 1382260 (Python Code)

Max Activating Token Index: 957

Text #7

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5355. Min Act: -0.0002

Data Index: 1584638 (Python Code)

Max Activating Token Index: 188

Text #8

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5215. Min Act: -0.0002

Data Index: 1622715 (Python Code)

Max Activating Token Index: 831

Text #9

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5192. Min Act: -0.0002

Data Index: 1522546 (Python Code)

Max Activating Token Index: 803

Text #10

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5150. Min Act: -0.0002

Data Index: 1422453 (Python Code)

Max Activating Token Index: 454

Text #11

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5151. Min Act: -0.0002

Data Index: 1553978 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5138. Min Act: -0.0002

Data Index: 1383309 (Python Code)

Max Activating Token Index: 677

Text #13

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5195. Min Act: -0.0002

Data Index: 1575163 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5115. Min Act: -0.0002

Data Index: 1444909 (Python Code)

Max Activating Token Index: 394

Text #15

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5218. Min Act: -0.0002

Data Index: 1637590 (Python Code)

Max Activating Token Index: 581

Text #16

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5153. Min Act: -0.0002

Data Index: 1405538 (Python Code)

Max Activating Token Index: 749

Text #17

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5116. Min Act: -0.0002

Data Index: 1630076 (Python Code)

Max Activating Token Index: 870

Text #18

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5084. Min Act: -0.0002

Data Index: 1635041 (Python Code)

Max Activating Token Index: 103

Text #19

Max Range: 0.6189. Min Range: -0.6189

Max Act: 0.5165. Min Act: -0.0002

Data Index: 1507581 (Python Code)

Max Activating Token Index: 391