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

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

Neuron 1607 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3704. Min Range: -1.3704

Max Act: 1.3704. Min Act: -0.0000

Data Index: 150638 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 1.3704. Min Range: -1.3704

Max Act: 1.2400. Min Act: -0.0001

Data Index: 405218 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 1.3704. Min Range: -1.3704

Max Act: 1.1966. Min Act: -0.0000

Data Index: 1036344 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 1.3704. Min Range: -1.3704

Max Act: 1.1252. Min Act: -0.0000

Data Index: 519557 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 1.3704. Min Range: -1.3704

Max Act: 1.0516. Min Act: -0.0001

Data Index: 984664 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1273343 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1339813 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9763. Min Act: -0.0000

Data Index: 452620 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.8714. Min Act: -0.0000

Data Index: 546497 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9569. Min Act: -0.0000

Data Index: 2886 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1309806 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.6900. Min Act: -0.0000

Data Index: 372867 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.7793. Min Act: -0.0000

Data Index: 781759 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9370. Min Act: -0.0000

Data Index: 1228434 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9413. Min Act: -0.0000

Data Index: 296845 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1299554 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9626. Min Act: -0.0000

Data Index: 900064 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.8744. Min Act: -0.0000

Data Index: 723492 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.8908. Min Act: -0.0000

Data Index: 285539 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.8766. Min Act: -0.0000

Data Index: 464341 (C4 (Web Text))

Max Activating Token Index: 872