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

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

Neuron 2820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1877. Min Act: -0.0000

Data Index: 942384 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1734. Min Act: -0.0000

Data Index: 516698 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1769. Min Act: -0.0000

Data Index: 422732 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1311516 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1397. Min Act: -0.0000

Data Index: 597200 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1520. Min Act: -0.0000

Data Index: 49793 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1543. Min Act: -0.0000

Data Index: 781386 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1357353 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1379. Min Act: -0.0000

Data Index: 724065 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1041082 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1328022 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1344. Min Act: -0.0000

Data Index: 571507 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1285. Min Act: -0.0000

Data Index: 529847 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1242. Min Act: -0.0000

Data Index: 529870 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1163. Min Act: -0.0000

Data Index: 287483 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1252. Min Act: -0.0000

Data Index: 967854 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1042845 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1174. Min Act: -0.0000

Data Index: 864815 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1251. Min Act: -0.0000

Data Index: 501799 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1150. Min Act: -0.0000

Data Index: 566981 (C4 (Web Text))

Max Activating Token Index: 203