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

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

Neuron 3430 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.8468. Min Act: -0.0001

Data Index: 1515920 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7924. Min Act: -0.0001

Data Index: 1410597 (Python Code)

Max Activating Token Index: 894

Text #2

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7818. Min Act: -0.0001

Data Index: 1488004 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7057. Min Act: -0.0001

Data Index: 1384808 (Python Code)

Max Activating Token Index: 231

Text #4

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7180. Min Act: -0.0001

Data Index: 1486569 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7336. Min Act: -0.0001

Data Index: 1569334 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6929. Min Act: -0.0001

Data Index: 1631757 (Python Code)

Max Activating Token Index: 39

Text #7

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6664. Min Act: -0.0001

Data Index: 1475667 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6448. Min Act: -0.0001

Data Index: 1369801 (Python Code)

Max Activating Token Index: 712

Text #9

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7071. Min Act: -0.0001

Data Index: 1441020 (Python Code)

Max Activating Token Index: 161

Text #10

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6765. Min Act: -0.0001

Data Index: 1572799 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6736. Min Act: -0.0001

Data Index: 1653408 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6766. Min Act: -0.0001

Data Index: 1424486 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7160. Min Act: -0.0002

Data Index: 1543420 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1415007 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6496. Min Act: -0.0001

Data Index: 1389087 (Python Code)

Max Activating Token Index: 164

Text #16

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6899. Min Act: -0.0001

Data Index: 1493665 (Python Code)

Max Activating Token Index: 62

Text #17

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6705. Min Act: -0.0001

Data Index: 1564410 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6437. Min Act: -0.0001

Data Index: 1435498 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.7156. Min Act: -0.0001

Data Index: 1616071 (Python Code)

Max Activating Token Index: 381