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

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

Neuron 452 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.7484. Min Act: -0.0000

Data Index: 239183 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.3258. Min Act: -0.0000

Data Index: 359175 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1170483 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.2150. Min Act: -0.0000

Data Index: 337561 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.2223. Min Act: 0.0000

Data Index: 892763 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.2069. Min Act: -0.0000

Data Index: 616495 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.1644. Min Act: 0.0000

Data Index: 143512 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.2061. Min Act: -0.0000

Data Index: 529008 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.1267. Min Act: -0.0000

Data Index: 614997 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.1188. Min Act: -0.0000

Data Index: 1003946 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.0918. Min Act: 0.0001

Data Index: 95037 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.0653. Min Act: -0.0000

Data Index: 238316 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.0453. Min Act: -0.0000

Data Index: 542462 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.0826. Min Act: 0.0001

Data Index: 1034550 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.0395. Min Act: -0.0000

Data Index: 221368 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 1.7484. Min Range: -1.7484

Max Act: 1.0127. Min Act: -0.0000

Data Index: 921626 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 1.7484. Min Range: -1.7484

Max Act: 0.9540. Min Act: -0.0000

Data Index: 732095 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.7484. Min Range: -1.7484

Max Act: 0.9397. Min Act: -0.0000

Data Index: 476435 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 1.7484. Min Range: -1.7484

Max Act: 0.9629. Min Act: -0.0000

Data Index: 456884 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 1.7484. Min Range: -1.7484

Max Act: 0.8609. Min Act: 0.0000

Data Index: 166690 (C4 (Web Text))

Max Activating Token Index: 131