Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3058 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3279. Min Act: -0.0003

Data Index: 1309203 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3761. Min Act: -0.0003

Data Index: 965108 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3507. Min Act: -0.0003

Data Index: 1036480 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3260. Min Act: -0.0003

Data Index: 730678 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2826. Min Act: -0.0003

Data Index: 242378 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3398. Min Act: -0.0003

Data Index: 845237 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3395. Min Act: -0.0003

Data Index: 271000 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3199. Min Act: -0.0003

Data Index: 533433 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3328. Min Act: -0.0003

Data Index: 791628 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3332. Min Act: -0.0003

Data Index: 673942 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3131. Min Act: -0.0003

Data Index: 1016338 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3174. Min Act: -0.0003

Data Index: 843131 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3255. Min Act: -0.0003

Data Index: 256836 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3244. Min Act: -0.0003

Data Index: 602510 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3131. Min Act: -0.0003

Data Index: 843283 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3246. Min Act: -0.0003

Data Index: 210633 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3249. Min Act: -0.0003

Data Index: 1206876 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3399. Min Act: -0.0003

Data Index: 331559 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3221. Min Act: -0.0003

Data Index: 1262766 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3379. Min Act: -0.0003

Data Index: 1230781 (C4 (Web Text))

Max Activating Token Index: 507