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

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

Neuron 1964 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.5440. Min Act: -0.0000

Data Index: 44057 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.5296. Min Act: -0.0000

Data Index: 758506 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.4649. Min Act: -0.0000

Data Index: 64179 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.3426. Min Act: -0.0000

Data Index: 540561 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.3311. Min Act: -0.0000

Data Index: 899891 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.4175. Min Act: -0.0000

Data Index: 528491 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.4018. Min Act: -0.0000

Data Index: 1322918 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.3938. Min Act: -0.0000

Data Index: 534219 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1301682 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.3418. Min Act: -0.0000

Data Index: 330264 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1060757 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.2290. Min Act: -0.0000

Data Index: 697775 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.3883. Min Act: -0.0000

Data Index: 536411 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.3794. Min Act: -0.0000

Data Index: 401132 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.2345. Min Act: -0.0000

Data Index: 762268 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.2503. Min Act: -0.0000

Data Index: 213486 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.3021. Min Act: -0.0000

Data Index: 251356 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.1916. Min Act: -0.0000

Data Index: 924785 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.2251. Min Act: -0.0000

Data Index: 488685 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 1.5440. Min Range: -1.5440

Max Act: 1.2568. Min Act: -0.0000

Data Index: 1260171 (C4 (Web Text))

Max Activating Token Index: 148