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

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

Neuron 3820 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: 0.9747. Min Range: -0.9747

Max Act: 0.9620. Min Act: -0.0002

Data Index: 1599460 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9608. Min Act: -0.0002

Data Index: 1528773 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9724. Min Act: -0.0002

Data Index: 1607664 (Python Code)

Max Activating Token Index: 118

Text #3

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9693. Min Act: -0.0002

Data Index: 1508703 (Python Code)

Max Activating Token Index: 138

Text #4

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9314. Min Act: -0.0002

Data Index: 1494476 (Python Code)

Max Activating Token Index: 630

Text #5

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9467. Min Act: -0.0002

Data Index: 1453161 (Python Code)

Max Activating Token Index: 50

Text #6

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9747. Min Act: -0.0002

Data Index: 1436699 (Python Code)

Max Activating Token Index: 162

Text #7

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9290. Min Act: -0.0002

Data Index: 1541432 (Python Code)

Max Activating Token Index: 769

Text #8

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9228. Min Act: -0.0002

Data Index: 1542121 (Python Code)

Max Activating Token Index: 744

Text #9

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9234. Min Act: -0.0002

Data Index: 1368782 (Python Code)

Max Activating Token Index: 905

Text #10

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9295. Min Act: -0.0002

Data Index: 1589584 (Python Code)

Max Activating Token Index: 790

Text #11

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9130. Min Act: -0.0002

Data Index: 1405145 (Python Code)

Max Activating Token Index: 276

Text #12

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9405. Min Act: -0.0002

Data Index: 1623848 (Python Code)

Max Activating Token Index: 744

Text #13

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8976. Min Act: -0.0002

Data Index: 1508572 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9104. Min Act: -0.0002

Data Index: 1449503 (Python Code)

Max Activating Token Index: 442

Text #15

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8913. Min Act: -0.0002

Data Index: 1561090 (Python Code)

Max Activating Token Index: 731

Text #16

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9094. Min Act: -0.0002

Data Index: 1586583 (Python Code)

Max Activating Token Index: 236

Text #17

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8970. Min Act: -0.0002

Data Index: 1499016 (Python Code)

Max Activating Token Index: 560

Text #18

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9054. Min Act: -0.0002

Data Index: 1375146 (Python Code)

Max Activating Token Index: 103

Text #19

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.9073. Min Act: -0.0002

Data Index: 1537830 (Python Code)

Max Activating Token Index: 642