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

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

Neuron 2716 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2235. Min Act: -0.0001

Data Index: 550556 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2174. Min Act: -0.0001

Data Index: 904624 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2093. Min Act: -0.0001

Data Index: 22743 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2182. Min Act: -0.0001

Data Index: 883948 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1948. Min Act: -0.0001

Data Index: 208148 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1866. Min Act: -0.0001

Data Index: 383040 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1807. Min Act: -0.0001

Data Index: 844301 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1806. Min Act: -0.0001

Data Index: 488260 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1871. Min Act: -0.0001

Data Index: 893884 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1858. Min Act: -0.0001

Data Index: 530777 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1847. Min Act: -0.0001

Data Index: 491701 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1792. Min Act: -0.0001

Data Index: 925314 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1841. Min Act: -0.0001

Data Index: 424820 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1781. Min Act: -0.0001

Data Index: 758544 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1825. Min Act: -0.0001

Data Index: 330014 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1837. Min Act: -0.0001

Data Index: 238942 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1813. Min Act: -0.0001

Data Index: 1229137 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1803. Min Act: -0.0001

Data Index: 391097 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1853. Min Act: -0.0001

Data Index: 1007479 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1849. Min Act: -0.0001

Data Index: 31260 (C4 (Web Text))

Max Activating Token Index: 109