Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 918 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0041. Min Act: -0.0002

Data Index: 1566275 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1428081 (Python Code)

Max Activating Token Index: 713

Text #2

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1421379 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1442552 (Python Code)

Max Activating Token Index: 279

Text #4

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0039. Min Act: -0.0003

Data Index: 1517183 (Python Code)

Max Activating Token Index: 851

Text #5

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1490044 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1653720 (Python Code)

Max Activating Token Index: 701

Text #7

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1439861 (Python Code)

Max Activating Token Index: 386

Text #8

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1410226 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1393003 (Python Code)

Max Activating Token Index: 785

Text #10

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1433562 (Python Code)

Max Activating Token Index: 737

Text #11

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1506915 (Python Code)

Max Activating Token Index: 785

Text #12

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1552636 (Python Code)

Max Activating Token Index: 809

Text #13

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1632583 (Python Code)

Max Activating Token Index: 391

Text #14

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1432744 (Python Code)

Max Activating Token Index: 320

Text #15

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1531813 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1576199 (Python Code)

Max Activating Token Index: 217

Text #17

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1544219 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1580449 (Python Code)

Max Activating Token Index: 832

Text #19

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1420094 (Python Code)

Max Activating Token Index: 386