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

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

Neuron 3326 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: 0.9837. Min Range: -0.9837

Max Act: 0.9253. Min Act: -0.0000

Data Index: 78315 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.9197. Min Act: -0.0000

Data Index: 376543 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.9837. Min Act: -0.0000

Data Index: 1250744 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.8550. Min Act: -0.0000

Data Index: 826644 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.8326. Min Act: -0.0000

Data Index: 151394 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7807. Min Act: 0.0000

Data Index: 682317 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.8521. Min Act: -0.0000

Data Index: 404639 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7749. Min Act: -0.0000

Data Index: 146542 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7609. Min Act: -0.0000

Data Index: 35926 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7371. Min Act: 0.0000

Data Index: 493405 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1028581 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1057368 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7423. Min Act: -0.0000

Data Index: 127883 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7412. Min Act: 0.0000

Data Index: 918876 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7547. Min Act: -0.0000

Data Index: 234000 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.6869. Min Act: -0.0000

Data Index: 446936 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1203724 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7647. Min Act: -0.0000

Data Index: 632486 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7348. Min Act: -0.0000

Data Index: 760219 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7260. Min Act: -0.0000

Data Index: 856064 (C4 (Web Text))

Max Activating Token Index: 613