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

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

Neuron 4613 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1907. Min Act: -0.0001

Data Index: 173280 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1676. Min Act: -0.0001

Data Index: 20459 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1833. Min Act: -0.0001

Data Index: 323879 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1575. Min Act: -0.0001

Data Index: 89860 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1405. Min Act: -0.0001

Data Index: 163796 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1511. Min Act: -0.0001

Data Index: 83141 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1551. Min Act: -0.0001

Data Index: 821815 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1077. Min Act: -0.0001

Data Index: 678646 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1579. Min Act: -0.0001

Data Index: 730868 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1452. Min Act: -0.0001

Data Index: 200434 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1089873 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1540. Min Act: -0.0001

Data Index: 797133 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1504. Min Act: -0.0001

Data Index: 495810 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1352. Min Act: -0.0001

Data Index: 450410 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1427. Min Act: -0.0001

Data Index: 557796 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1258207 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1358. Min Act: -0.0001

Data Index: 167871 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1031864 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1333. Min Act: -0.0001

Data Index: 67704 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1461999 (Python Code)

Max Activating Token Index: 1012