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

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

Neuron 650 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: 0.9231. Min Range: -0.9231

Max Act: 0.9231. Min Act: -0.0002

Data Index: 1368700 (Python Code)

Max Activating Token Index: 217

Text #1

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.9137. Min Act: -0.0002

Data Index: 1624012 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.9112. Min Act: -0.0002

Data Index: 1565769 (Python Code)

Max Activating Token Index: 97

Text #3

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.9024. Min Act: -0.0002

Data Index: 1595603 (Python Code)

Max Activating Token Index: 688

Text #4

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8944. Min Act: -0.0002

Data Index: 1590457 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8716. Min Act: -0.0002

Data Index: 1496253 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8607. Min Act: -0.0002

Data Index: 1375586 (Python Code)

Max Activating Token Index: 147

Text #7

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8599. Min Act: -0.0002

Data Index: 1530880 (Python Code)

Max Activating Token Index: 203

Text #8

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8510. Min Act: -0.0002

Data Index: 1576412 (Python Code)

Max Activating Token Index: 243

Text #9

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8409. Min Act: -0.0002

Data Index: 1580118 (Python Code)

Max Activating Token Index: 536

Text #10

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8600. Min Act: -0.0002

Data Index: 1399643 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8459. Min Act: -0.0002

Data Index: 1374830 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8277. Min Act: -0.0002

Data Index: 1654302 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8282. Min Act: -0.0002

Data Index: 1492361 (Python Code)

Max Activating Token Index: 48

Text #14

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8043. Min Act: -0.0002

Data Index: 1529932 (Python Code)

Max Activating Token Index: 630

Text #15

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8053. Min Act: -0.0002

Data Index: 1632798 (Python Code)

Max Activating Token Index: 781

Text #16

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7966. Min Act: -0.0002

Data Index: 1585262 (Python Code)

Max Activating Token Index: 233

Text #17

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8067. Min Act: -0.0002

Data Index: 1584768 (Python Code)

Max Activating Token Index: 647

Text #18

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8030. Min Act: -0.0002

Data Index: 1616116 (Python Code)

Max Activating Token Index: 521

Text #19

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7917. Min Act: -0.0002

Data Index: 1585384 (Python Code)

Max Activating Token Index: 271