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

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

Neuron 5804 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.9536. Min Act: -0.0000

Data Index: 630124 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.9865. Min Act: -0.0000

Data Index: 137497 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.9010. Min Act: -0.0000

Data Index: 928376 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.8485. Min Act: -0.0000

Data Index: 217834 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1197809 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.7445. Min Act: -0.0000

Data Index: 778043 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.7377. Min Act: -0.0000

Data Index: 165430 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1013808 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.7337. Min Act: -0.0000

Data Index: 699082 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.6880. Min Act: -0.0000

Data Index: 49817 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1273511 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.7003. Min Act: -0.0000

Data Index: 206539 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1460139 (Python Code)

Max Activating Token Index: 448

Text #13

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.6639. Min Act: -0.0000

Data Index: 850050 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.7043. Min Act: -0.0000

Data Index: 123044 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1295514 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.6836. Min Act: -0.0000

Data Index: 328727 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.6600. Min Act: -0.0000

Data Index: 411254 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.6580. Min Act: -0.0000

Data Index: 511269 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.9865. Min Range: -0.9865

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1448652 (Python Code)

Max Activating Token Index: 302