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

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

Neuron 1673 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.6538. Min Act: -0.0000

Data Index: 1379919 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.4414. Min Act: -0.0000

Data Index: 1620045 (Python Code)

Max Activating Token Index: 683

Text #2

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.3301. Min Act: -0.0000

Data Index: 1507729 (Python Code)

Max Activating Token Index: 811

Text #3

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.5815. Min Act: -0.0000

Data Index: 1418970 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.3887. Min Act: -0.0000

Data Index: 1375450 (Python Code)

Max Activating Token Index: 680

Text #5

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.3412. Min Act: -0.0000

Data Index: 1498824 (Python Code)

Max Activating Token Index: 262

Text #6

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.3974. Min Act: -0.0000

Data Index: 1554896 (Python Code)

Max Activating Token Index: 628

Text #7

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.5513. Min Act: -0.0001

Data Index: 1481050 (Python Code)

Max Activating Token Index: 47

Text #8

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.5279. Min Act: -0.0000

Data Index: 1452682 (Python Code)

Max Activating Token Index: 266

Text #9

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.3879. Min Act: -0.0000

Data Index: 1366306 (Python Code)

Max Activating Token Index: 629

Text #10

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.2148. Min Act: -0.0000

Data Index: 1403753 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.3634. Min Act: -0.0000

Data Index: 1429476 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.3896. Min Act: -0.0000

Data Index: 1423752 (Python Code)

Max Activating Token Index: 249

Text #13

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.5255. Min Act: -0.0000

Data Index: 1403068 (Python Code)

Max Activating Token Index: 622

Text #14

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.3664. Min Act: -0.0000

Data Index: 1434720 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.3519. Min Act: -0.0000

Data Index: 1472496 (Python Code)

Max Activating Token Index: 733

Text #16

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.3676. Min Act: -0.0001

Data Index: 1564131 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.3946. Min Act: -0.0000

Data Index: 1583937 (Python Code)

Max Activating Token Index: 281

Text #18

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.5235. Min Act: -0.0000

Data Index: 1432016 (Python Code)

Max Activating Token Index: 936

Text #19

Max Range: 3.6538. Min Range: -3.6538

Max Act: 3.5144. Min Act: -0.0000

Data Index: 1538665 (Python Code)

Max Activating Token Index: 239