Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3476 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2233. Min Act: -0.0001

Data Index: 967488 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2230. Min Act: -0.0000

Data Index: 732007 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2107. Min Act: -0.0001

Data Index: 837346 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1972. Min Act: -0.0001

Data Index: 596791 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2046. Min Act: -0.0001

Data Index: 224745 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1972. Min Act: -0.0001

Data Index: 406950 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2012. Min Act: -0.0001

Data Index: 1203161 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1253335 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1898. Min Act: -0.0001

Data Index: 335367 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1310626 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1313829 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1995. Min Act: -0.0000

Data Index: 38659 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1930. Min Act: -0.0000

Data Index: 107438 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1890. Min Act: -0.0001

Data Index: 576693 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1908. Min Act: -0.0001

Data Index: 929921 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1356241 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1805. Min Act: -0.0001

Data Index: 638795 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1786. Min Act: -0.0000

Data Index: 562804 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1706. Min Act: -0.0000

Data Index: 456653 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1283663 (C4 (Web Text))

Max Activating Token Index: 362