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

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

Neuron 3444 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9561. Min Act: -0.0001

Data Index: 1446173 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8323. Min Act: -0.0001

Data Index: 1412066 (Python Code)

Max Activating Token Index: 171

Text #2

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8821. Min Act: -0.0001

Data Index: 1384770 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1608943 (Python Code)

Max Activating Token Index: 977

Text #4

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8893. Min Act: -0.0001

Data Index: 1475180 (Python Code)

Max Activating Token Index: 116

Text #5

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8026. Min Act: -0.0001

Data Index: 1522766 (Python Code)

Max Activating Token Index: 457

Text #6

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8006. Min Act: -0.0001

Data Index: 1650768 (Python Code)

Max Activating Token Index: 923

Text #7

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8101. Min Act: -0.0001

Data Index: 1553560 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8033. Min Act: -0.0001

Data Index: 1539327 (Python Code)

Max Activating Token Index: 583

Text #9

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7404. Min Act: -0.0001

Data Index: 1591299 (Python Code)

Max Activating Token Index: 989

Text #10

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7866. Min Act: -0.0001

Data Index: 1429709 (Python Code)

Max Activating Token Index: 896

Text #11

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8408. Min Act: -0.0001

Data Index: 1633634 (Python Code)

Max Activating Token Index: 806

Text #12

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7867. Min Act: -0.0001

Data Index: 1520579 (Python Code)

Max Activating Token Index: 227

Text #13

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7109. Min Act: -0.0001

Data Index: 1414921 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7832. Min Act: -0.0001

Data Index: 1507569 (Python Code)

Max Activating Token Index: 426

Text #15

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7275. Min Act: -0.0001

Data Index: 1589833 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1636604 (Python Code)

Max Activating Token Index: 990

Text #17

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1542798 (Python Code)

Max Activating Token Index: 515

Text #18

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8323. Min Act: -0.0001

Data Index: 1539147 (Python Code)

Max Activating Token Index: 637

Text #19

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7873. Min Act: -0.0001

Data Index: 1416589 (Python Code)

Max Activating Token Index: 280