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

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

Neuron 6122 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1238141 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1148529 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4305. Min Act: -0.0000

Data Index: 122456 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4245. Min Act: -0.0000

Data Index: 914248 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3749. Min Act: -0.0000

Data Index: 600531 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3777. Min Act: -0.0000

Data Index: 246238 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3779. Min Act: -0.0000

Data Index: 321675 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3882. Min Act: -0.0000

Data Index: 756583 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3826. Min Act: -0.0000

Data Index: 680426 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4018. Min Act: -0.0000

Data Index: 679566 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3686. Min Act: -0.0000

Data Index: 495690 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3773. Min Act: -0.0000

Data Index: 879645 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3679. Min Act: -0.0000

Data Index: 978145 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1332486 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3505. Min Act: -0.0000

Data Index: 499573 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3832. Min Act: -0.0000

Data Index: 258968 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3577. Min Act: -0.0000

Data Index: 596991 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3355. Min Act: -0.0000

Data Index: 180922 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1138638 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3335. Min Act: -0.0000

Data Index: 746497 (C4 (Web Text))

Max Activating Token Index: 70