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

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

Neuron 2185 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6714. Min Act: -0.0001

Data Index: 1585300 (Python Code)

Max Activating Token Index: 276

Text #1

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6589. Min Act: -0.0001

Data Index: 1425506 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6618. Min Act: -0.0001

Data Index: 1465742 (Python Code)

Max Activating Token Index: 519

Text #3

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6078. Min Act: -0.0001

Data Index: 1407893 (Python Code)

Max Activating Token Index: 647

Text #4

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5127. Min Act: -0.0001

Data Index: 1478378 (Python Code)

Max Activating Token Index: 764

Text #5

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5049. Min Act: -0.0001

Data Index: 1363879 (Python Code)

Max Activating Token Index: 641

Text #6

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5106. Min Act: -0.0001

Data Index: 1368549 (Python Code)

Max Activating Token Index: 191

Text #7

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.4943. Min Act: -0.0001

Data Index: 1627144 (Python Code)

Max Activating Token Index: 429

Text #8

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.4904. Min Act: -0.0001

Data Index: 1640243 (Python Code)

Max Activating Token Index: 469

Text #9

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5222. Min Act: -0.0001

Data Index: 1580642 (Python Code)

Max Activating Token Index: 632

Text #10

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5665. Min Act: -0.0001

Data Index: 1650085 (Python Code)

Max Activating Token Index: 223

Text #11

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5208. Min Act: -0.0001

Data Index: 1449124 (Python Code)

Max Activating Token Index: 426

Text #12

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5000. Min Act: -0.0001

Data Index: 1649437 (Python Code)

Max Activating Token Index: 760

Text #13

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.4667. Min Act: -0.0001

Data Index: 1366169 (Python Code)

Max Activating Token Index: 327

Text #14

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5029. Min Act: -0.0001

Data Index: 1575626 (Python Code)

Max Activating Token Index: 932

Text #15

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5102. Min Act: -0.0001

Data Index: 1521870 (Python Code)

Max Activating Token Index: 481

Text #16

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.4579. Min Act: -0.0001

Data Index: 1575939 (Python Code)

Max Activating Token Index: 540

Text #17

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.4559. Min Act: -0.0001

Data Index: 1592314 (Python Code)

Max Activating Token Index: 340

Text #18

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.4048. Min Act: -0.0001

Data Index: 1520202 (Python Code)

Max Activating Token Index: 384

Text #19

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.4805. Min Act: -0.0001

Data Index: 1612384 (Python Code)

Max Activating Token Index: 403