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

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

Neuron 2312 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.2807. Min Act: -0.0000

Data Index: 716233 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.7618. Min Act: -0.0000

Data Index: 806937 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.4201. Min Act: -0.0000

Data Index: 213036 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.4852. Min Act: -0.0000

Data Index: 512306 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.2324. Min Act: -0.0000

Data Index: 899123 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 2.7618. Min Range: -2.7618

Max Act: 1.9846. Min Act: -0.0000

Data Index: 556959 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.1511. Min Act: -0.0000

Data Index: 372053 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.3870. Min Act: -0.0000

Data Index: 1354240 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.3822. Min Act: -0.0000

Data Index: 1024773 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.2680. Min Act: -0.0000

Data Index: 699565 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.0177. Min Act: -0.0000

Data Index: 724679 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.1147. Min Act: -0.0000

Data Index: 506487 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.0152. Min Act: -0.0000

Data Index: 594278 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.0913. Min Act: -0.0000

Data Index: 552099 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.2119. Min Act: -0.0000

Data Index: 33838 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.1816. Min Act: -0.0000

Data Index: 375120 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.0694. Min Act: -0.0000

Data Index: 614806 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.0620. Min Act: -0.0000

Data Index: 207088 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.0273. Min Act: -0.0000

Data Index: 99967 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 2.7618. Min Range: -2.7618

Max Act: 2.0147. Min Act: -0.0000

Data Index: 830207 (C4 (Web Text))

Max Activating Token Index: 1003