Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 953 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0242. Min Range: -4.0242

Max Act: 4.0242. Min Act: -0.0000

Data Index: 149397 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 4.0242. Min Range: -4.0242

Max Act: 3.2814. Min Act: -0.0000

Data Index: 83678 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.5754. Min Act: -0.0000

Data Index: 1104397 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 4.0242. Min Range: -4.0242

Max Act: 3.1381. Min Act: -0.0000

Data Index: 1181960 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 4.0242. Min Range: -4.0242

Max Act: 3.2529. Min Act: -0.0000

Data Index: 673256 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 4.0242. Min Range: -4.0242

Max Act: 3.0529. Min Act: -0.0000

Data Index: 734590 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.9051. Min Act: -0.0000

Data Index: 37820 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 4.0242. Min Range: -4.0242

Max Act: 3.1692. Min Act: -0.0000

Data Index: 1036349 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.7692. Min Act: -0.0000

Data Index: 590192 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.7133. Min Act: -0.0000

Data Index: 582061 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.6077. Min Act: -0.0000

Data Index: 331362 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.3327. Min Act: -0.0000

Data Index: 313858 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.2971. Min Act: -0.0000

Data Index: 99027 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.5257. Min Act: -0.0000

Data Index: 838749 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.3824. Min Act: -0.0000

Data Index: 1158672 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.2590. Min Act: -0.0000

Data Index: 479353 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.3531. Min Act: -0.0000

Data Index: 589562 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.6174. Min Act: -0.0000

Data Index: 1224236 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.4417. Min Act: -0.0000

Data Index: 352208 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 4.0242. Min Range: -4.0242

Max Act: 2.5430. Min Act: -0.0000

Data Index: 1277445 (C4 (Web Text))

Max Activating Token Index: 443