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

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

Neuron 781 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0708. Min Act: -0.0001

Data Index: 139764 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1276156 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0580. Min Act: -0.0001

Data Index: 759501 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1274980 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0665. Min Act: -0.0001

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0597. Min Act: -0.0001

Data Index: 27204 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0534. Min Act: -0.0001

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0544. Min Act: -0.0001

Data Index: 553294 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0565. Min Act: -0.0001

Data Index: 180148 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1320772 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0326. Min Act: -0.0001

Data Index: 460697 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0491. Min Act: -0.0001

Data Index: 473521 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0521. Min Act: -0.0001

Data Index: 559563 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1328626 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0543. Min Act: -0.0001

Data Index: 549630 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0556. Min Act: -0.0001

Data Index: 714444 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0509. Min Act: -0.0001

Data Index: 108944 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1074330 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0488. Min Act: -0.0001

Data Index: 43995 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0486. Min Act: -0.0001

Data Index: 758310 (C4 (Web Text))

Max Activating Token Index: 705