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

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

Neuron 5915 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1136473 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1915. Min Act: -0.0001

Data Index: 949273 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1978. Min Act: -0.0001

Data Index: 741872 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1952. Min Act: -0.0001

Data Index: 254593 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1959. Min Act: -0.0001

Data Index: 180279 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1851. Min Act: -0.0001

Data Index: 1039864 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1067057 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1928. Min Act: -0.0001

Data Index: 1231154 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1512. Min Act: -0.0001

Data Index: 516169 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1982. Min Act: -0.0001

Data Index: 883143 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1806. Min Act: -0.0001

Data Index: 330692 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1798. Min Act: -0.0002

Data Index: 1037713 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1665. Min Act: -0.0001

Data Index: 53862 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1897. Min Act: -0.0001

Data Index: 55687 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1644. Min Act: -0.0001

Data Index: 1455992 (Python Code)

Max Activating Token Index: 610

Text #15

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1734. Min Act: -0.0001

Data Index: 191109 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1810. Min Act: -0.0001

Data Index: 458974 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1663. Min Act: -0.0001

Data Index: 1119516 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1645. Min Act: -0.0001

Data Index: 411773 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1820. Min Act: -0.0001

Data Index: 551362 (C4 (Web Text))

Max Activating Token Index: 226