Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4046 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.6882. Min Act: -0.0000

Data Index: 610386 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1216393 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5472. Min Act: -0.0000

Data Index: 89598 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5336. Min Act: -0.0001

Data Index: 58647 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5298. Min Act: -0.0000

Data Index: 857552 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5068. Min Act: -0.0000

Data Index: 738793 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4825. Min Act: -0.0000

Data Index: 419394 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4917. Min Act: -0.0000

Data Index: 962986 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4692. Min Act: -0.0000

Data Index: 437778 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4684. Min Act: -0.0000

Data Index: 71037 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4669. Min Act: -0.0000

Data Index: 263106 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4497. Min Act: -0.0000

Data Index: 60037 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4626. Min Act: -0.0000

Data Index: 849116 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4296. Min Act: -0.0000

Data Index: 891462 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4556. Min Act: -0.0000

Data Index: 561622 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4361. Min Act: -0.0000

Data Index: 919643 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4288. Min Act: -0.0000

Data Index: 515982 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1152342 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4137. Min Act: -0.0000

Data Index: 508367 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1228041 (C4 (Web Text))

Max Activating Token Index: 807