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

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

Neuron 3497 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: 0.2721. Min Range: -0.2721

Max Act: 0.2721. Min Act: -0.0000

Data Index: 216645 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1335731 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2162. Min Act: -0.0000

Data Index: 771987 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2066. Min Act: -0.0000

Data Index: 781278 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1149710 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2019. Min Act: -0.0000

Data Index: 919469 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1938. Min Act: -0.0000

Data Index: 56798 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2007. Min Act: -0.0000

Data Index: 982193 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1287049 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2003. Min Act: -0.0000

Data Index: 32262 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1770. Min Act: -0.0000

Data Index: 66437 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1903. Min Act: -0.0000

Data Index: 35569 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1884. Min Act: -0.0000

Data Index: 478528 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1055251 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1816. Min Act: -0.0000

Data Index: 133454 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1913. Min Act: -0.0000

Data Index: 62386 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1851. Min Act: -0.0000

Data Index: 379452 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1897. Min Act: -0.0000

Data Index: 888931 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1851. Min Act: -0.0000

Data Index: 930740 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1727. Min Act: -0.0000

Data Index: 786236 (C4 (Web Text))

Max Activating Token Index: 756