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

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

Neuron 2557 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: 2.0406. Min Range: -2.0406

Max Act: 2.0406. Min Act: -0.0000

Data Index: 1457198 (Python Code)

Max Activating Token Index: 513

Text #1

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.9886. Min Act: -0.0000

Data Index: 1098535 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.9609. Min Act: -0.0000

Data Index: 290627 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.8478. Min Act: -0.0000

Data Index: 230078 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.8362. Min Act: -0.0000

Data Index: 206374 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.7766. Min Act: -0.0000

Data Index: 692126 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.8781. Min Act: -0.0000

Data Index: 776432 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.5562. Min Act: -0.0000

Data Index: 1040941 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.7249. Min Act: -0.0000

Data Index: 394283 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.7183. Min Act: -0.0000

Data Index: 1031258 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.6422. Min Act: -0.0000

Data Index: 1056186 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.6368. Min Act: -0.0000

Data Index: 108357 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.4587. Min Act: -0.0000

Data Index: 779033 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.6387. Min Act: -0.0000

Data Index: 493933 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.4996. Min Act: -0.0000

Data Index: 381904 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.5833. Min Act: -0.0000

Data Index: 739318 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.4867. Min Act: -0.0000

Data Index: 140636 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.5758. Min Act: -0.0000

Data Index: 1058942 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.5634. Min Act: -0.0000

Data Index: 472614 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 2.0406. Min Range: -2.0406

Max Act: 1.6407. Min Act: -0.0000

Data Index: 758694 (C4 (Web Text))

Max Activating Token Index: 919