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

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

Neuron 3258 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: 0.6805. Min Range: -0.6805

Max Act: 0.6805. Min Act: -0.0000

Data Index: 617138 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5992. Min Act: -0.0000

Data Index: 207346 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5582. Min Act: -0.0000

Data Index: 769482 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5170. Min Act: -0.0000

Data Index: 795431 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5022. Min Act: -0.0000

Data Index: 594281 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4993. Min Act: -0.0000

Data Index: 162640 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4913. Min Act: -0.0000

Data Index: 279884 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4804. Min Act: -0.0000

Data Index: 837948 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4850. Min Act: -0.0000

Data Index: 531454 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4460. Min Act: -0.0000

Data Index: 914304 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4602. Min Act: -0.0000

Data Index: 879393 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4619. Min Act: -0.0000

Data Index: 467425 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4365. Min Act: -0.0000

Data Index: 114836 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4192. Min Act: -0.0000

Data Index: 911037 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4582. Min Act: -0.0000

Data Index: 649698 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4593. Min Act: -0.0000

Data Index: 297988 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1256860 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4330. Min Act: -0.0000

Data Index: 600707 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4225. Min Act: -0.0000

Data Index: 106730 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4361. Min Act: -0.0000

Data Index: 134288 (C4 (Web Text))

Max Activating Token Index: 476