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

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

Neuron 3241 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.3472. Min Act: 0.0000

Data Index: 1640437 (Python Code)

Max Activating Token Index: 397

Text #1

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.2832. Min Act: 0.0000

Data Index: 1653039 (Python Code)

Max Activating Token Index: 335

Text #2

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1911. Min Act: 0.0000

Data Index: 1492259 (Python Code)

Max Activating Token Index: 328

Text #3

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1317. Min Act: 0.0000

Data Index: 1588799 (Python Code)

Max Activating Token Index: 369

Text #4

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1488721 (Python Code)

Max Activating Token Index: 635

Text #5

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9201. Min Act: -0.0000

Data Index: 1652762 (Python Code)

Max Activating Token Index: 203

Text #6

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9111. Min Act: 0.0000

Data Index: 1387186 (Python Code)

Max Activating Token Index: 1017

Text #7

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9358. Min Act: 0.0000

Data Index: 1466556 (Python Code)

Max Activating Token Index: 275

Text #8

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1447462 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8837. Min Act: 0.0000

Data Index: 1401039 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8151. Min Act: 0.0000

Data Index: 1638647 (Python Code)

Max Activating Token Index: 101

Text #11

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1366852 (Python Code)

Max Activating Token Index: 380

Text #12

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7585. Min Act: -0.0000

Data Index: 1617985 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1616790 (Python Code)

Max Activating Token Index: 879

Text #14

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1618270 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1560389 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1391370 (Python Code)

Max Activating Token Index: 837

Text #17

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1511182 (Python Code)

Max Activating Token Index: 225

Text #18

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1635896 (Python Code)

Max Activating Token Index: 855

Text #19

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1369592 (Python Code)

Max Activating Token Index: 668