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

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

Neuron 5867 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1692. Min Range: -2.1692

Max Act: 2.1692. Min Act: -0.0000

Data Index: 1550009 (Python Code)

Max Activating Token Index: 389

Text #1

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.9523. Min Act: -0.0000

Data Index: 1429513 (Python Code)

Max Activating Token Index: 246

Text #2

Max Range: 2.1692. Min Range: -2.1692

Max Act: 2.0384. Min Act: -0.0000

Data Index: 1474800 (Python Code)

Max Activating Token Index: 322

Text #3

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.8037. Min Act: -0.0000

Data Index: 1500140 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.9685. Min Act: -0.0000

Data Index: 1377555 (Python Code)

Max Activating Token Index: 711

Text #5

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.8565. Min Act: -0.0000

Data Index: 1516497 (Python Code)

Max Activating Token Index: 389

Text #6

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.8334. Min Act: -0.0000

Data Index: 1452988 (Python Code)

Max Activating Token Index: 766

Text #7

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.7220. Min Act: -0.0000

Data Index: 1501455 (Python Code)

Max Activating Token Index: 391

Text #8

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.6598. Min Act: -0.0000

Data Index: 1485557 (Python Code)

Max Activating Token Index: 401

Text #9

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.6713. Min Act: -0.0000

Data Index: 1495125 (Python Code)

Max Activating Token Index: 468

Text #10

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.8230. Min Act: -0.0000

Data Index: 1472550 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.7198. Min Act: -0.0000

Data Index: 1499752 (Python Code)

Max Activating Token Index: 969

Text #12

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.7099. Min Act: -0.0000

Data Index: 1550636 (Python Code)

Max Activating Token Index: 201

Text #13

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.6840. Min Act: -0.0000

Data Index: 1502122 (Python Code)

Max Activating Token Index: 407

Text #14

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.6949. Min Act: -0.0000

Data Index: 1406548 (Python Code)

Max Activating Token Index: 1019

Text #15

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.6042. Min Act: -0.0000

Data Index: 1388625 (Python Code)

Max Activating Token Index: 512

Text #16

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.6425. Min Act: -0.0000

Data Index: 1507598 (Python Code)

Max Activating Token Index: 521

Text #17

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.7312. Min Act: -0.0000

Data Index: 1601277 (Python Code)

Max Activating Token Index: 857

Text #18

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.5976. Min Act: -0.0000

Data Index: 1565598 (Python Code)

Max Activating Token Index: 333

Text #19

Max Range: 2.1692. Min Range: -2.1692

Max Act: 1.7767. Min Act: -0.0000

Data Index: 1429375 (Python Code)

Max Activating Token Index: 306