Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1149 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0504. Min Act: -0.0002

Data Index: 530970 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0469. Min Act: -0.0002

Data Index: 961472 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0500. Min Act: -0.0002

Data Index: 986831 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1066636 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0426. Min Act: -0.0002

Data Index: 694238 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0475. Min Act: -0.0002

Data Index: 455123 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0408. Min Act: -0.0001

Data Index: 1299899 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0408. Min Act: -0.0002

Data Index: 57483 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0403. Min Act: -0.0002

Data Index: 36794 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1229053 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0467. Min Act: -0.0001

Data Index: 443815 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1142880 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0401. Min Act: -0.0002

Data Index: 25890 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1336733 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0408. Min Act: -0.0001

Data Index: 378323 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0407. Min Act: -0.0001

Data Index: 696471 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0443. Min Act: -0.0002

Data Index: 665188 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0397. Min Act: -0.0001

Data Index: 897741 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1114277 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0386. Min Act: -0.0001

Data Index: 898133 (C4 (Web Text))

Max Activating Token Index: 269