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

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

Neuron 5823 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: 1.0394. Min Range: -1.0394

Max Act: 1.0394. Min Act: -0.0001

Data Index: 1452824 (Python Code)

Max Activating Token Index: 931

Text #1

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.9477. Min Act: -0.0001

Data Index: 143443 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 1.0394. Min Range: -1.0394

Max Act: 1.0324. Min Act: -0.0001

Data Index: 113663 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.9001. Min Act: -0.0001

Data Index: 171859 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.9430. Min Act: -0.0001

Data Index: 1082877 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.9354. Min Act: -0.0001

Data Index: 681578 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8097. Min Act: -0.0001

Data Index: 220928 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.7905. Min Act: -0.0001

Data Index: 334304 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8086. Min Act: -0.0001

Data Index: 339285 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.7219. Min Act: -0.0001

Data Index: 367097 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.8016. Min Act: -0.0001

Data Index: 714686 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.6937. Min Act: -0.0001

Data Index: 631960 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.5914. Min Act: -0.0001

Data Index: 506273 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.6927. Min Act: -0.0001

Data Index: 1285767 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.6266. Min Act: -0.0001

Data Index: 499815 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.6674. Min Act: -0.0001

Data Index: 1605696 (Python Code)

Max Activating Token Index: 454

Text #16

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.7207. Min Act: -0.0001

Data Index: 1085563 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.6571. Min Act: -0.0001

Data Index: 260155 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.6122. Min Act: -0.0001

Data Index: 1263568 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.0394. Min Range: -1.0394

Max Act: 0.6454. Min Act: -0.0001

Data Index: 855423 (C4 (Web Text))

Max Activating Token Index: 242