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

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

Neuron 1650 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.8309. Min Act: -0.0003

Data Index: 1569153 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.7387. Min Act: -0.0003

Data Index: 1596743 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.5938. Min Act: -0.0004

Data Index: 1630574 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.5285. Min Act: -0.0003

Data Index: 1466985 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.5443. Min Act: -0.0003

Data Index: 1484802 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.4667. Min Act: -0.0003

Data Index: 1515926 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.4464. Min Act: -0.0003

Data Index: 1617180 (Python Code)

Max Activating Token Index: 430

Text #7

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.4759. Min Act: -0.0003

Data Index: 1466677 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.4310. Min Act: -0.0003

Data Index: 1379532 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.4342. Min Act: -0.0003

Data Index: 1635104 (Python Code)

Max Activating Token Index: 408

Text #10

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.4290. Min Act: -0.0003

Data Index: 1378894 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.4411. Min Act: -0.0003

Data Index: 1433033 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.3784. Min Act: -0.0003

Data Index: 1442088 (Python Code)

Max Activating Token Index: 605

Text #13

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.4628. Min Act: -0.0003

Data Index: 1490712 (Python Code)

Max Activating Token Index: 518

Text #14

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.3905. Min Act: -0.0003

Data Index: 1525365 (Python Code)

Max Activating Token Index: 379

Text #15

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.3997. Min Act: -0.0003

Data Index: 1489909 (Python Code)

Max Activating Token Index: 164

Text #16

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.3598. Min Act: -0.0003

Data Index: 1577079 (Python Code)

Max Activating Token Index: 620

Text #17

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.4121. Min Act: -0.0003

Data Index: 1603204 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.4403. Min Act: -0.0003

Data Index: 1656700 (Python Code)

Max Activating Token Index: 535

Text #19

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.3570. Min Act: -0.0003

Data Index: 1447636 (Python Code)

Max Activating Token Index: 547