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

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

Neuron 2994 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1274744 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1132522 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1117931 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1333. Min Act: -0.0001

Data Index: 1151194 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1423. Min Act: -0.0001

Data Index: 552277 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1041585 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1184. Min Act: -0.0001

Data Index: 767695 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1207. Min Act: -0.0001

Data Index: 955404 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1296161 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1117. Min Act: -0.0001

Data Index: 35781 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1150. Min Act: -0.0001

Data Index: 676015 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1098352 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1156. Min Act: -0.0001

Data Index: 353559 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1088. Min Act: -0.0001

Data Index: 513188 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1138. Min Act: -0.0001

Data Index: 477753 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1091. Min Act: -0.0001

Data Index: 170395 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1067. Min Act: -0.0001

Data Index: 498258 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1048. Min Act: -0.0001

Data Index: 946362 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1014. Min Act: -0.0001

Data Index: 390173 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1006. Min Act: -0.0001

Data Index: 732758 (C4 (Web Text))

Max Activating Token Index: 761