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

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

Neuron 3344 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1394347 (Python Code)

Max Activating Token Index: 516

Text #1

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1469354 (Python Code)

Max Activating Token Index: 560

Text #2

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1488904 (Python Code)

Max Activating Token Index: 888

Text #3

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1373045 (Python Code)

Max Activating Token Index: 615

Text #4

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1405516 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1456402 (Python Code)

Max Activating Token Index: 251

Text #6

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1530403 (Python Code)

Max Activating Token Index: 891

Text #7

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1522200 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6867. Min Act: -0.0000

Data Index: 833689 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1361134 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1371848 (Python Code)

Max Activating Token Index: 922

Text #11

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6335. Min Act: -0.0000

Data Index: 811314 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6090. Min Act: -0.0000

Data Index: 905434 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5523. Min Act: -0.0000

Data Index: 741946 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6146. Min Act: -0.0000

Data Index: 285511 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1173398 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1510981 (Python Code)

Max Activating Token Index: 487

Text #17

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5762. Min Act: -0.0000

Data Index: 871710 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1640288 (Python Code)

Max Activating Token Index: 604

Text #19

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1522115 (Python Code)

Max Activating Token Index: 363