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

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

Neuron 3963 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: 1.9019. Min Range: -1.9019

Max Act: 1.9019. Min Act: -0.0000

Data Index: 1651700 (Python Code)

Max Activating Token Index: 795

Text #1

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1455230 (Python Code)

Max Activating Token Index: 508

Text #2

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.0729. Min Act: -0.0000

Data Index: 1519503 (Python Code)

Max Activating Token Index: 629

Text #3

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1425617 (Python Code)

Max Activating Token Index: 54

Text #4

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1456011 (Python Code)

Max Activating Token Index: 263

Text #5

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1631788 (Python Code)

Max Activating Token Index: 81

Text #6

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1512212 (Python Code)

Max Activating Token Index: 564

Text #7

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1467205 (Python Code)

Max Activating Token Index: 761

Text #8

Max Range: 1.9019. Min Range: -1.9019

Max Act: 1.1320. Min Act: -0.0000

Data Index: 1570784 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.8308. Min Act: -0.0000

Data Index: 439725 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1485711 (Python Code)

Max Activating Token Index: 589

Text #11

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1384367 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.8549. Min Act: -0.0000

Data Index: 800612 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.7859. Min Act: -0.0000

Data Index: 716074 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.7707. Min Act: -0.0000

Data Index: 1373311 (Python Code)

Max Activating Token Index: 784

Text #15

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1422355 (Python Code)

Max Activating Token Index: 590

Text #16

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1600036 (Python Code)

Max Activating Token Index: 561

Text #17

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1536373 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1431084 (Python Code)

Max Activating Token Index: 425

Text #19

Max Range: 1.9019. Min Range: -1.9019

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1527247 (Python Code)

Max Activating Token Index: 789