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

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

Neuron 3152 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: 1.3409. Min Range: -1.3409

Max Act: 1.3409. Min Act: -0.0000

Data Index: 358587 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.3199. Min Act: -0.0000

Data Index: 1303327 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1729. Min Act: -0.0000

Data Index: 883944 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1017467 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1456. Min Act: -0.0000

Data Index: 149299 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0650. Min Act: -0.0000

Data Index: 760518 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1792. Min Act: -0.0000

Data Index: 459176 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1072. Min Act: -0.0000

Data Index: 522683 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1061488 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1257. Min Act: -0.0000

Data Index: 1180399 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1317939 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1556. Min Act: -0.0000

Data Index: 223870 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1401. Min Act: -0.0000

Data Index: 801780 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.2669. Min Act: -0.0000

Data Index: 498756 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0620. Min Act: -0.0000

Data Index: 871215 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0516. Min Act: -0.0000

Data Index: 250393 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1446. Min Act: -0.0000

Data Index: 3185 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1810. Min Act: -0.0000

Data Index: 873394 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1045. Min Act: -0.0000

Data Index: 1077829 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1618. Min Act: -0.0000

Data Index: 375137 (C4 (Web Text))

Max Activating Token Index: 697