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

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

Neuron 2326 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.6490. Min Act: -0.0000

Data Index: 1175923 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.9989. Min Act: -0.0000

Data Index: 962874 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.6980. Min Act: -0.0000

Data Index: 383131 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.7530. Min Act: -0.0000

Data Index: 714237 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.6463. Min Act: -0.0000

Data Index: 417724 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.5915. Min Act: -0.0000

Data Index: 827683 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.3910. Min Act: -0.0000

Data Index: 1048108 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1118609 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.3379. Min Act: -0.0000

Data Index: 821503 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.3778. Min Act: -0.0000

Data Index: 272779 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1103873 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.2435. Min Act: -0.0000

Data Index: 270906 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1517255 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.1855. Min Act: -0.0000

Data Index: 950370 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.1238. Min Act: -0.0000

Data Index: 222304 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.2042. Min Act: -0.0000

Data Index: 160065 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1249532 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.1562. Min Act: -0.0000

Data Index: 1145513 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.2165. Min Act: -0.0000

Data Index: 621605 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 1.9989. Min Range: -1.9989

Max Act: 1.1827. Min Act: -0.0000

Data Index: 22042 (C4 (Web Text))

Max Activating Token Index: 620