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

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

Neuron 2699 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1061350 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2401. Min Act: -0.0001

Data Index: 6377 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2253. Min Act: -0.0000

Data Index: 364376 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2145. Min Act: -0.0000

Data Index: 390053 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2038. Min Act: -0.0001

Data Index: 329890 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1880. Min Act: -0.0000

Data Index: 339348 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1160895 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1926. Min Act: -0.0000

Data Index: 962227 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1073493 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1766. Min Act: -0.0000

Data Index: 529419 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1787. Min Act: -0.0001

Data Index: 304079 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1646. Min Act: -0.0000

Data Index: 779243 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1633. Min Act: -0.0000

Data Index: 185993 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1106595 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1629. Min Act: 0.0000

Data Index: 1164376 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1496. Min Act: -0.0000

Data Index: 804403 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1490. Min Act: -0.0000

Data Index: 323988 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1548. Min Act: -0.0000

Data Index: 789193 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1550. Min Act: -0.0000

Data Index: 281573 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1497. Min Act: -0.0000

Data Index: 24413 (C4 (Web Text))

Max Activating Token Index: 518