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

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

Neuron 5426 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2898. Min Range: -1.2898

Max Act: 1.2898. Min Act: -0.0000

Data Index: 1530106 (Python Code)

Max Activating Token Index: 902

Text #1

Max Range: 1.2898. Min Range: -1.2898

Max Act: 1.1785. Min Act: -0.0000

Data Index: 268489 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 1.2898. Min Range: -1.2898

Max Act: 1.1114. Min Act: -0.0000

Data Index: 286446 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.2898. Min Range: -1.2898

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1333662 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.9765. Min Act: -0.0000

Data Index: 617442 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1235541 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 1.2898. Min Range: -1.2898

Max Act: 1.0101. Min Act: -0.0000

Data Index: 693120 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1218610 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1075757 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8855. Min Act: -0.0000

Data Index: 369725 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8548. Min Act: -0.0000

Data Index: 887731 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8702. Min Act: -0.0000

Data Index: 322909 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8823. Min Act: -0.0000

Data Index: 816277 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8805. Min Act: -0.0000

Data Index: 696936 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8192. Min Act: -0.0000

Data Index: 618242 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1277042 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8138. Min Act: -0.0000

Data Index: 471636 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7556. Min Act: -0.0000

Data Index: 441244 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7447. Min Act: -0.0000

Data Index: 858243 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7443. Min Act: -0.0000

Data Index: 754459 (C4 (Web Text))

Max Activating Token Index: 511