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

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

Neuron 2487 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4416. Min Range: -2.4416

Max Act: 2.4416. Min Act: -0.0000

Data Index: 1401404 (Python Code)

Max Activating Token Index: 478

Text #1

Max Range: 2.4416. Min Range: -2.4416

Max Act: 2.2247. Min Act: -0.0000

Data Index: 1466813 (Python Code)

Max Activating Token Index: 933

Text #2

Max Range: 2.4416. Min Range: -2.4416

Max Act: 2.2040. Min Act: -0.0000

Data Index: 1499682 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.9720. Min Act: -0.0000

Data Index: 1590284 (Python Code)

Max Activating Token Index: 293

Text #4

Max Range: 2.4416. Min Range: -2.4416

Max Act: 2.1069. Min Act: -0.0000

Data Index: 1627463 (Python Code)

Max Activating Token Index: 134

Text #5

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.9506. Min Act: -0.0000

Data Index: 1623935 (Python Code)

Max Activating Token Index: 941

Text #6

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.8455. Min Act: -0.0000

Data Index: 1514008 (Python Code)

Max Activating Token Index: 950

Text #7

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.7190. Min Act: -0.0000

Data Index: 1441710 (Python Code)

Max Activating Token Index: 630

Text #8

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.8722. Min Act: -0.0000

Data Index: 1611405 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.7581. Min Act: -0.0000

Data Index: 1632366 (Python Code)

Max Activating Token Index: 54

Text #10

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.7646. Min Act: -0.0000

Data Index: 1630250 (Python Code)

Max Activating Token Index: 718

Text #11

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.9443. Min Act: -0.0000

Data Index: 1482292 (Python Code)

Max Activating Token Index: 799

Text #12

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.6812. Min Act: -0.0000

Data Index: 1612737 (Python Code)

Max Activating Token Index: 662

Text #13

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.8504. Min Act: -0.0000

Data Index: 1638082 (Python Code)

Max Activating Token Index: 998

Text #14

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.6945. Min Act: -0.0000

Data Index: 1372480 (Python Code)

Max Activating Token Index: 371

Text #15

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.6009. Min Act: -0.0000

Data Index: 1486327 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.6668. Min Act: -0.0000

Data Index: 1618983 (Python Code)

Max Activating Token Index: 948

Text #17

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.7813. Min Act: -0.0000

Data Index: 1402805 (Python Code)

Max Activating Token Index: 619

Text #18

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.6993. Min Act: -0.0000

Data Index: 1577391 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 2.4416. Min Range: -2.4416

Max Act: 1.5179. Min Act: -0.0000

Data Index: 1540237 (Python Code)

Max Activating Token Index: 180