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

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

Neuron 3053 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: 0.3720. Min Range: -0.3720

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1456457 (Python Code)

Max Activating Token Index: 676

Text #1

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1477911 (Python Code)

Max Activating Token Index: 934

Text #2

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1364006 (Python Code)

Max Activating Token Index: 601

Text #3

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1451896 (Python Code)

Max Activating Token Index: 432

Text #4

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1412794 (Python Code)

Max Activating Token Index: 565

Text #5

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1587364 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1485533 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1473257 (Python Code)

Max Activating Token Index: 920

Text #8

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1436083 (Python Code)

Max Activating Token Index: 197

Text #9

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1568273 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1404533 (Python Code)

Max Activating Token Index: 416

Text #11

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2134. Min Act: -0.0000

Data Index: 1652430 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1509804 (Python Code)

Max Activating Token Index: 403

Text #13

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1512979 (Python Code)

Max Activating Token Index: 942

Text #14

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1417987 (Python Code)

Max Activating Token Index: 424

Text #15

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2106. Min Act: -0.0000

Data Index: 79407 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1483112 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1501839 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1517040 (Python Code)

Max Activating Token Index: 94

Text #19

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1572264 (Python Code)

Max Activating Token Index: 81