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

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

Neuron 2021 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.3533. Min Act: -0.0000

Data Index: 918452 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2872. Min Act: -0.0000

Data Index: 1311879 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2729. Min Act: -0.0000

Data Index: 1312386 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2312. Min Act: -0.0000

Data Index: 1416778 (Python Code)

Max Activating Token Index: 821

Text #4

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1099766 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1092. Min Act: -0.0000

Data Index: 714729 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2693. Min Act: -0.0000

Data Index: 261582 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2683. Min Act: -0.0000

Data Index: 273574 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1683. Min Act: -0.0000

Data Index: 407617 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1529. Min Act: -0.0000

Data Index: 910060 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1496. Min Act: -0.0000

Data Index: 1211153 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1557. Min Act: -0.0000

Data Index: 199259 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2400. Min Act: -0.0000

Data Index: 1468683 (Python Code)

Max Activating Token Index: 986

Text #13

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1966. Min Act: -0.0000

Data Index: 310074 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1151379 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1471. Min Act: -0.0000

Data Index: 1608233 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1056. Min Act: -0.0000

Data Index: 923828 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1343. Min Act: -0.0000

Data Index: 951572 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.0807. Min Act: -0.0000

Data Index: 309176 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1416. Min Act: -0.0000

Data Index: 744801 (C4 (Web Text))

Max Activating Token Index: 933