Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 984 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1744. Min Act: -0.0001

Data Index: 16252 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1637. Min Act: -0.0001

Data Index: 91199 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1642. Min Act: -0.0001

Data Index: 894803 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1453. Min Act: -0.0001

Data Index: 39654 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1495. Min Act: -0.0001

Data Index: 955126 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1431. Min Act: -0.0001

Data Index: 235729 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1418. Min Act: -0.0001

Data Index: 777256 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1468. Min Act: -0.0001

Data Index: 992043 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1458. Min Act: -0.0001

Data Index: 55494 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1381. Min Act: -0.0001

Data Index: 501745 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1010393 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1367. Min Act: -0.0001

Data Index: 495955 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1358. Min Act: -0.0001

Data Index: 81825 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1428. Min Act: -0.0001

Data Index: 644866 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1167470 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1395. Min Act: -0.0001

Data Index: 888649 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1184927 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1318. Min Act: -0.0001

Data Index: 260989 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1309. Min Act: -0.0001

Data Index: 34148 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1293. Min Act: -0.0001

Data Index: 945137 (C4 (Web Text))

Max Activating Token Index: 792