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

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

Neuron 3689 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1629755 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1446443 (Python Code)

Max Activating Token Index: 726

Text #2

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1531598 (Python Code)

Max Activating Token Index: 875

Text #3

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1550724 (Python Code)

Max Activating Token Index: 819

Text #4

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1554168 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1487755 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1607523 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1052085 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1375264 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1106446 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1612153 (Python Code)

Max Activating Token Index: 945

Text #11

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0964. Min Act: -0.0000

Data Index: 18002 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1604451 (Python Code)

Max Activating Token Index: 635

Text #13

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1404144 (Python Code)

Max Activating Token Index: 809

Text #14

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1432628 (Python Code)

Max Activating Token Index: 501

Text #15

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1502153 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1392019 (Python Code)

Max Activating Token Index: 364

Text #17

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0933. Min Act: -0.0000

Data Index: 200279 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0920. Min Act: -0.0000

Data Index: 331404 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1589192 (Python Code)

Max Activating Token Index: 874