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

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

Neuron 1482 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.2838. Min Act: -0.0001

Data Index: 1464458 (Python Code)

Max Activating Token Index: 947

Text #1

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.3602. Min Act: -0.0001

Data Index: 1407675 (Python Code)

Max Activating Token Index: 864

Text #2

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.0532. Min Act: -0.0001

Data Index: 1412962 (Python Code)

Max Activating Token Index: 704

Text #3

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.0146. Min Act: -0.0000

Data Index: 303590 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 1.3602. Min Range: -1.3602

Max Act: 1.0101. Min Act: -0.0000

Data Index: 12406 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.9931. Min Act: -0.0001

Data Index: 1567036 (Python Code)

Max Activating Token Index: 668

Text #6

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.9247. Min Act: -0.0001

Data Index: 1637384 (Python Code)

Max Activating Token Index: 915

Text #7

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1270041 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.8764. Min Act: -0.0001

Data Index: 1550463 (Python Code)

Max Activating Token Index: 1021

Text #9

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.8088. Min Act: -0.0001

Data Index: 1299743 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.7659. Min Act: -0.0000

Data Index: 568772 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1081402 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.8836. Min Act: -0.0001

Data Index: 1523670 (Python Code)

Max Activating Token Index: 513

Text #13

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.8043. Min Act: -0.0000

Data Index: 133073 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.8243. Min Act: -0.0001

Data Index: 1631650 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1296655 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.7688. Min Act: -0.0001

Data Index: 1446456 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.7588. Min Act: -0.0001

Data Index: 190487 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.7616. Min Act: -0.0001

Data Index: 1161226 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 1.3602. Min Range: -1.3602

Max Act: 0.7667. Min Act: -0.0001

Data Index: 589084 (C4 (Web Text))

Max Activating Token Index: 685