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

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

Neuron 1942 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2893. Min Act: -0.0000

Data Index: 92754 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1146582 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2357. Min Act: -0.0000

Data Index: 313590 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2187. Min Act: -0.0000

Data Index: 371460 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1984. Min Act: -0.0000

Data Index: 54925 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1119141 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1017035 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1200769 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1955. Min Act: -0.0000

Data Index: 266742 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1935. Min Act: -0.0000

Data Index: 871558 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1890. Min Act: -0.0000

Data Index: 379781 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1826. Min Act: -0.0000

Data Index: 969238 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1815. Min Act: -0.0000

Data Index: 228318 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1046444 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1901. Min Act: -0.0000

Data Index: 616381 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1825. Min Act: -0.0000

Data Index: 661639 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1892. Min Act: -0.0000

Data Index: 229082 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1352818 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1875. Min Act: -0.0000

Data Index: 52619 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1712. Min Act: -0.0000

Data Index: 799664 (C4 (Web Text))

Max Activating Token Index: 954