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

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

Neuron 4314 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0447. Min Act: -0.0000

Data Index: 286179 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1472729 (Python Code)

Max Activating Token Index: 146

Text #2

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1434407 (Python Code)

Max Activating Token Index: 959

Text #3

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8151. Min Act: -0.0000

Data Index: 8570 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1637762 (Python Code)

Max Activating Token Index: 780

Text #5

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1490283 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1626415 (Python Code)

Max Activating Token Index: 213

Text #7

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1477444 (Python Code)

Max Activating Token Index: 158

Text #8

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1582017 (Python Code)

Max Activating Token Index: 162

Text #9

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1608910 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1559828 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1445282 (Python Code)

Max Activating Token Index: 674

Text #12

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1493978 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1418744 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1593074 (Python Code)

Max Activating Token Index: 448

Text #15

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1616050 (Python Code)

Max Activating Token Index: 683

Text #16

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1636555 (Python Code)

Max Activating Token Index: 195

Text #17

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1632273 (Python Code)

Max Activating Token Index: 753

Text #18

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1424962 (Python Code)

Max Activating Token Index: 628

Text #19

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1386785 (Python Code)

Max Activating Token Index: 129