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

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

Neuron 5307 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1441727 (Python Code)

Max Activating Token Index: 262

Text #1

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7760. Min Act: -0.0001

Data Index: 1399043 (Python Code)

Max Activating Token Index: 213

Text #2

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7642. Min Act: -0.0001

Data Index: 1517527 (Python Code)

Max Activating Token Index: 373

Text #3

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.8180. Min Act: -0.0001

Data Index: 1473503 (Python Code)

Max Activating Token Index: 842

Text #4

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7035. Min Act: -0.0001

Data Index: 1361552 (Python Code)

Max Activating Token Index: 362

Text #5

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7503. Min Act: -0.0001

Data Index: 1553258 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7013. Min Act: -0.0001

Data Index: 1656256 (Python Code)

Max Activating Token Index: 440

Text #7

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6602. Min Act: -0.0001

Data Index: 1509274 (Python Code)

Max Activating Token Index: 300

Text #8

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6771. Min Act: -0.0001

Data Index: 1507243 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6795. Min Act: -0.0001

Data Index: 1568754 (Python Code)

Max Activating Token Index: 718

Text #10

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7236. Min Act: -0.0001

Data Index: 1470301 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6793. Min Act: -0.0001

Data Index: 1528893 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6746. Min Act: -0.0001

Data Index: 1551715 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7173. Min Act: -0.0001

Data Index: 1427187 (Python Code)

Max Activating Token Index: 352

Text #14

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6211. Min Act: -0.0001

Data Index: 1423736 (Python Code)

Max Activating Token Index: 993

Text #15

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6782. Min Act: -0.0001

Data Index: 1521703 (Python Code)

Max Activating Token Index: 974

Text #16

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6235. Min Act: -0.0001

Data Index: 1519607 (Python Code)

Max Activating Token Index: 853

Text #17

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6545. Min Act: -0.0001

Data Index: 1617330 (Python Code)

Max Activating Token Index: 491

Text #18

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6207. Min Act: -0.0001

Data Index: 1369506 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.6365. Min Act: -0.0001

Data Index: 1531108 (Python Code)

Max Activating Token Index: 773