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

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

Neuron 1714 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.7795. Min Act: -0.0001

Data Index: 1054302 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.6832. Min Act: -0.0001

Data Index: 782004 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1236410 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.5162. Min Act: -0.0001

Data Index: 1271269 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1353868 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1394876 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.5141. Min Act: -0.0001

Data Index: 1241377 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4767. Min Act: -0.0001

Data Index: 1154285 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.5072. Min Act: -0.0001

Data Index: 1452396 (Python Code)

Max Activating Token Index: 738

Text #9

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.3623. Min Act: -0.0001

Data Index: 1450943 (Python Code)

Max Activating Token Index: 565

Text #10

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4089. Min Act: -0.0001

Data Index: 706747 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.3801. Min Act: -0.0001

Data Index: 1563402 (Python Code)

Max Activating Token Index: 599

Text #12

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4216. Min Act: -0.0001

Data Index: 1539906 (Python Code)

Max Activating Token Index: 247

Text #13

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4365. Min Act: -0.0001

Data Index: 903965 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.3893. Min Act: -0.0001

Data Index: 1039851 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4684. Min Act: -0.0001

Data Index: 1653391 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.3978. Min Act: -0.0001

Data Index: 390229 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.4390. Min Act: -0.0001

Data Index: 520809 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.3898. Min Act: -0.0001

Data Index: 24878 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.7795. Min Range: -0.7795

Max Act: 0.3644. Min Act: -0.0001

Data Index: 1537087 (Python Code)

Max Activating Token Index: 723