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

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

Neuron 4262 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1350272 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0534. Min Act: -0.0000

Data Index: 669460 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0472. Min Act: -0.0000

Data Index: 891943 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0379. Min Act: -0.0000

Data Index: 357432 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0404. Min Act: -0.0000

Data Index: 761166 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0387. Min Act: -0.0000

Data Index: 933544 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0370. Min Act: -0.0000

Data Index: 119498 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0441. Min Act: -0.0000

Data Index: 1342492 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0363. Min Act: -0.0000

Data Index: 808373 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0347. Min Act: -0.0000

Data Index: 573570 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0330. Min Act: -0.0000

Data Index: 742473 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0356. Min Act: -0.0000

Data Index: 475280 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0354. Min Act: -0.0000

Data Index: 55502 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0327. Min Act: -0.0000

Data Index: 987559 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0344. Min Act: -0.0000

Data Index: 542963 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0323. Min Act: -0.0000

Data Index: 465491 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0322. Min Act: -0.0000

Data Index: 308061 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0317. Min Act: -0.0000

Data Index: 549534 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0317. Min Act: -0.0000

Data Index: 1174783 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0320. Min Act: -0.0000

Data Index: 325220 (C4 (Web Text))

Max Activating Token Index: 411