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

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

Neuron 550 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7360. Min Range: -7.7360

Max Act: 7.7360. Min Act: -0.0001

Data Index: 9946 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 7.7360. Min Range: -7.7360

Max Act: 7.6950. Min Act: -0.0001

Data Index: 346228 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 7.7360. Min Range: -7.7360

Max Act: 7.3246. Min Act: -0.0001

Data Index: 116981 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 7.7360. Min Range: -7.7360

Max Act: 7.1701. Min Act: -0.0001

Data Index: 770795 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.8760. Min Act: -0.0000

Data Index: 944225 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.8349. Min Act: -0.0001

Data Index: 370073 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.5239. Min Act: -0.0001

Data Index: 76969 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.9060. Min Act: -0.0001

Data Index: 210149 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.8639. Min Act: -0.0001

Data Index: 827949 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 7.7360. Min Range: -7.7360

Max Act: 7.0323. Min Act: -0.0001

Data Index: 415228 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.6654. Min Act: -0.0000

Data Index: 1287676 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.4677. Min Act: -0.0000

Data Index: 783536 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.7488. Min Act: -0.0001

Data Index: 1110813 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.0825. Min Act: -0.0000

Data Index: 1031367 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.8215. Min Act: -0.0001

Data Index: 1020158 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.4318. Min Act: -0.0001

Data Index: 96327 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.0973. Min Act: -0.0001

Data Index: 1313294 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.9579. Min Act: -0.0001

Data Index: 712501 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.7635. Min Act: -0.0001

Data Index: 514005 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 7.7360. Min Range: -7.7360

Max Act: 6.3895. Min Act: -0.0001

Data Index: 166037 (C4 (Web Text))

Max Activating Token Index: 451