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

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

Neuron 4153 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1465462 (Python Code)

Max Activating Token Index: 594

Text #1

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1571357 (Python Code)

Max Activating Token Index: 115

Text #2

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1629098 (Python Code)

Max Activating Token Index: 432

Text #3

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1515604 (Python Code)

Max Activating Token Index: 920

Text #4

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1459479 (Python Code)

Max Activating Token Index: 544

Text #5

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1648465 (Python Code)

Max Activating Token Index: 830

Text #6

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1447031 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1645681 (Python Code)

Max Activating Token Index: 480

Text #8

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1394172 (Python Code)

Max Activating Token Index: 703

Text #9

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1494407 (Python Code)

Max Activating Token Index: 810

Text #10

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1589803 (Python Code)

Max Activating Token Index: 389

Text #11

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1552732 (Python Code)

Max Activating Token Index: 391

Text #12

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1649073 (Python Code)

Max Activating Token Index: 373

Text #13

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1587106 (Python Code)

Max Activating Token Index: 760

Text #14

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1558471 (Python Code)

Max Activating Token Index: 361

Text #15

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1597782 (Python Code)

Max Activating Token Index: 925

Text #16

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1635936 (Python Code)

Max Activating Token Index: 965

Text #17

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1377366 (Python Code)

Max Activating Token Index: 155

Text #18

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1503419 (Python Code)

Max Activating Token Index: 729

Text #19

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1360588 (Python Code)

Max Activating Token Index: 800