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

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

Neuron 4757 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1019826 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7641. Min Act: -0.0000

Data Index: 286199 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7298. Min Act: -0.0000

Data Index: 714393 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1134196 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1628124 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6236. Min Act: -0.0000

Data Index: 660423 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.5965. Min Act: -0.0000

Data Index: 214878 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6307. Min Act: -0.0000

Data Index: 629641 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6113. Min Act: -0.0000

Data Index: 41160 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6037. Min Act: 0.0001

Data Index: 1628232 (Python Code)

Max Activating Token Index: 160

Text #10

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6074. Min Act: -0.0000

Data Index: 989257 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.5976. Min Act: 0.0000

Data Index: 67711 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.5878. Min Act: 0.0000

Data Index: 22833 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6259. Min Act: -0.0000

Data Index: 491006 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.5849. Min Act: 0.0000

Data Index: 193765 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.5432. Min Act: 0.0000

Data Index: 1589808 (Python Code)

Max Activating Token Index: 814

Text #16

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.5514. Min Act: -0.0000

Data Index: 912966 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1122290 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.5642. Min Act: -0.0000

Data Index: 743646 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.5802. Min Act: -0.0000

Data Index: 519398 (C4 (Web Text))

Max Activating Token Index: 28