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

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

Neuron 656 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.9586. Min Act: -0.0000

Data Index: 1160433 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 3.1002. Min Range: -3.1002

Max Act: 3.1002. Min Act: -0.0000

Data Index: 947625 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.7608. Min Act: -0.0000

Data Index: 748249 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.8482. Min Act: -0.0000

Data Index: 863057 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.7989. Min Act: -0.0000

Data Index: 719243 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.9375. Min Act: -0.0000

Data Index: 550340 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.6660. Min Act: -0.0000

Data Index: 651284 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.8672. Min Act: -0.0000

Data Index: 799629 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.7039. Min Act: -0.0000

Data Index: 406060 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.4692. Min Act: -0.0000

Data Index: 1350574 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.7072. Min Act: -0.0000

Data Index: 42005 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.4811. Min Act: -0.0000

Data Index: 480324 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.3516. Min Act: -0.0000

Data Index: 565585 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.2295. Min Act: -0.0000

Data Index: 581435 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.4618. Min Act: -0.0000

Data Index: 289972 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.4439. Min Act: -0.0000

Data Index: 1633433 (Python Code)

Max Activating Token Index: 420

Text #16

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.3037. Min Act: -0.0000

Data Index: 221159 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.6322. Min Act: -0.0000

Data Index: 1031484 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.2461. Min Act: -0.0000

Data Index: 1133002 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 3.1002. Min Range: -3.1002

Max Act: 2.4805. Min Act: -0.0000

Data Index: 264138 (C4 (Web Text))

Max Activating Token Index: 562