Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1508 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.6881. Min Act: -0.0000

Data Index: 1633570 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.5603. Min Act: -0.0000

Data Index: 1424112 (Python Code)

Max Activating Token Index: 962

Text #2

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.5037. Min Act: -0.0000

Data Index: 1238055 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.5077. Min Act: -0.0000

Data Index: 1654203 (Python Code)

Max Activating Token Index: 392

Text #4

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1553608 (Python Code)

Max Activating Token Index: 178

Text #5

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.3709. Min Act: -0.0000

Data Index: 59226 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.3147. Min Act: -0.0000

Data Index: 708589 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.2981. Min Act: -0.0000

Data Index: 742597 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.2290. Min Act: -0.0000

Data Index: 1200641 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.2810. Min Act: -0.0000

Data Index: 181395 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.2623. Min Act: -0.0000

Data Index: 858717 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.1744. Min Act: -0.0000

Data Index: 1276873 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.2161. Min Act: -0.0000

Data Index: 1284552 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.2000. Min Act: -0.0000

Data Index: 828355 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.2002. Min Act: -0.0000

Data Index: 554329 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.1922. Min Act: -0.0000

Data Index: 983925 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.1233. Min Act: -0.0000

Data Index: 708043 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.1803. Min Act: -0.0000

Data Index: 397401 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.1668. Min Act: -0.0000

Data Index: 643136 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 1.6881. Min Range: -1.6881

Max Act: 1.1970. Min Act: -0.0000

Data Index: 670720 (C4 (Web Text))

Max Activating Token Index: 856