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

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

Neuron 26 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1135345 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0883. Min Act: -0.0000

Data Index: 205425 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0815. Min Act: -0.0000

Data Index: 1072903 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1026742 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0561. Min Act: -0.0000

Data Index: 910244 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0736. Min Act: -0.0000

Data Index: 361959 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0751. Min Act: -0.0000

Data Index: 488514 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0710. Min Act: -0.0000

Data Index: 175970 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0697. Min Act: -0.0000

Data Index: 161209 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1104585 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1274499 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0478. Min Act: -0.0000

Data Index: 967606 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0556. Min Act: -0.0000

Data Index: 331204 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0595. Min Act: -0.0000

Data Index: 388175 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1024020 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1122927 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1616331 (Python Code)

Max Activating Token Index: 735

Text #17

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1321874 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0488. Min Act: -0.0000

Data Index: 705882 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0483. Min Act: -0.0000

Data Index: 152930 (C4 (Web Text))

Max Activating Token Index: 31