Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2385 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.9414. Min Act: -0.0000

Data Index: 519007 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1295879 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8291. Min Act: -0.0000

Data Index: 220614 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7702. Min Act: -0.0000

Data Index: 309146 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7764. Min Act: -0.0000

Data Index: 860180 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7234. Min Act: -0.0000

Data Index: 954677 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7109. Min Act: -0.0000

Data Index: 805072 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1176126 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6593. Min Act: -0.0000

Data Index: 356560 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1044266 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7401. Min Act: -0.0000

Data Index: 944659 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7032. Min Act: -0.0000

Data Index: 118442 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6157. Min Act: -0.0000

Data Index: 457156 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6363. Min Act: -0.0000

Data Index: 928699 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1015893 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6181. Min Act: -0.0000

Data Index: 703242 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6378. Min Act: -0.0000

Data Index: 398584 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.5924. Min Act: -0.0000

Data Index: 476632 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1049995 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.5986. Min Act: -0.0000

Data Index: 108062 (C4 (Web Text))

Max Activating Token Index: 292