Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1230 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1398. Min Act: -0.0003

Data Index: 1655305 (Python Code)

Max Activating Token Index: 226

Text #1

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1273. Min Act: -0.0003

Data Index: 1376961 (Python Code)

Max Activating Token Index: 931

Text #2

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1076. Min Act: -0.0003

Data Index: 849670 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1262. Min Act: -0.0003

Data Index: 166037 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1186. Min Act: -0.0003

Data Index: 1601066 (Python Code)

Max Activating Token Index: 140

Text #5

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1242. Min Act: -0.0003

Data Index: 1613846 (Python Code)

Max Activating Token Index: 28

Text #6

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1169. Min Act: -0.0003

Data Index: 1379539 (Python Code)

Max Activating Token Index: 255

Text #7

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1205. Min Act: -0.0003

Data Index: 1508710 (Python Code)

Max Activating Token Index: 295

Text #8

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1231. Min Act: -0.0003

Data Index: 1649891 (Python Code)

Max Activating Token Index: 926

Text #9

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1143. Min Act: -0.0003

Data Index: 1524185 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1103. Min Act: -0.0003

Data Index: 1529441 (Python Code)

Max Activating Token Index: 531

Text #11

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1080. Min Act: -0.0003

Data Index: 1391166 (Python Code)

Max Activating Token Index: 836

Text #12

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1068. Min Act: -0.0003

Data Index: 1277682 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1151. Min Act: -0.0003

Data Index: 1498898 (Python Code)

Max Activating Token Index: 179

Text #14

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1076. Min Act: -0.0003

Data Index: 1638979 (Python Code)

Max Activating Token Index: 508

Text #15

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1137. Min Act: -0.0003

Data Index: 331509 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1111. Min Act: -0.0003

Data Index: 1565993 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0955. Min Act: -0.0003

Data Index: 338217 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1079. Min Act: -0.0003

Data Index: 1421183 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1126. Min Act: -0.0003

Data Index: 1373285 (Python Code)

Max Activating Token Index: 264