Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1689 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1250555 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.7770. Min Act: -0.0001

Data Index: 94263 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.7246. Min Act: -0.0000

Data Index: 266521 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.7184. Min Act: -0.0000

Data Index: 92775 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1133484 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.7242. Min Act: -0.0001

Data Index: 751410 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.7108. Min Act: 0.0000

Data Index: 1266947 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1332726 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6515. Min Act: -0.0000

Data Index: 183866 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6844. Min Act: -0.0000

Data Index: 529825 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6830. Min Act: -0.0000

Data Index: 469669 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6723. Min Act: -0.0001

Data Index: 1235018 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6909. Min Act: -0.0000

Data Index: 53854 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6814. Min Act: -0.0000

Data Index: 850006 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6583. Min Act: -0.0001

Data Index: 378326 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1026278 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6243. Min Act: -0.0001

Data Index: 138082 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6388. Min Act: -0.0000

Data Index: 133914 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1315480 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.8224. Min Range: -0.8224

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1243160 (C4 (Web Text))

Max Activating Token Index: 954