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

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

Neuron 3274 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.2251. Min Act: -0.0000

Data Index: 964758 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.2093. Min Act: -0.0000

Data Index: 333936 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.2017. Min Act: -0.0000

Data Index: 899727 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1875. Min Act: -0.0000

Data Index: 217865 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1881. Min Act: -0.0000

Data Index: 633992 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1751. Min Act: -0.0000

Data Index: 222460 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1710. Min Act: -0.0000

Data Index: 944929 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1730. Min Act: -0.0000

Data Index: 813250 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1588. Min Act: -0.0000

Data Index: 664769 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1569. Min Act: -0.0000

Data Index: 728366 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1254409 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1565. Min Act: -0.0000

Data Index: 529289 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1633. Min Act: -0.0000

Data Index: 820248 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1579. Min Act: -0.0000

Data Index: 398785 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1552. Min Act: -0.0000

Data Index: 925954 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1486. Min Act: -0.0000

Data Index: 251208 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1204584 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1366. Min Act: -0.0000

Data Index: 171455 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1323189 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.2251. Min Range: -0.2251

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1156582 (C4 (Web Text))

Max Activating Token Index: 473