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

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

Neuron 2232 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.2938. Min Act: -0.0001

Data Index: 46237 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1118076 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.1756. Min Act: -0.0000

Data Index: 666125 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.2095. Min Act: -0.0000

Data Index: 850407 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.1279. Min Act: -0.0001

Data Index: 200649 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.1084. Min Act: -0.0001

Data Index: 349533 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 1.2938. Min Range: -1.2938

Max Act: 0.9437. Min Act: -0.0000

Data Index: 517120 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1088504 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.0398. Min Act: -0.0000

Data Index: 1006662 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.1132. Min Act: -0.0001

Data Index: 1254356 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.0122. Min Act: -0.0001

Data Index: 539742 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 1.2938. Min Range: -1.2938

Max Act: 0.9708. Min Act: -0.0001

Data Index: 1241465 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.0167. Min Act: -0.0001

Data Index: 342189 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 1.2938. Min Range: -1.2938

Max Act: 1.0213. Min Act: -0.0000

Data Index: 908349 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.2938. Min Range: -1.2938

Max Act: 0.9741. Min Act: -0.0000

Data Index: 371690 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.2938. Min Range: -1.2938

Max Act: 0.9124. Min Act: -0.0001

Data Index: 487915 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.2938. Min Range: -1.2938

Max Act: 0.9592. Min Act: -0.0001

Data Index: 107821 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.2938. Min Range: -1.2938

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1186801 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 1.2938. Min Range: -1.2938

Max Act: 0.8997. Min Act: -0.0001

Data Index: 461721 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 1.2938. Min Range: -1.2938

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1008637 (C4 (Web Text))

Max Activating Token Index: 147