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

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

Neuron 224 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3953. Min Act: -0.0002

Data Index: 1050581 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.4084. Min Act: -0.0002

Data Index: 680273 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3890. Min Act: -0.0002

Data Index: 446496 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3738. Min Act: -0.0002

Data Index: 1114566 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3788. Min Act: -0.0002

Data Index: 971815 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3672. Min Act: -0.0002

Data Index: 278941 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3751. Min Act: -0.0002

Data Index: 1303259 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3714. Min Act: -0.0002

Data Index: 1208187 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3641. Min Act: -0.0002

Data Index: 1106426 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3510. Min Act: -0.0002

Data Index: 951602 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3601. Min Act: -0.0002

Data Index: 1221948 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3709. Min Act: -0.0002

Data Index: 1049464 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3605. Min Act: -0.0002

Data Index: 888972 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3577. Min Act: -0.0002

Data Index: 740365 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3508. Min Act: -0.0002

Data Index: 215037 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3518. Min Act: -0.0002

Data Index: 377275 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3407. Min Act: -0.0002

Data Index: 861552 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3473. Min Act: -0.0002

Data Index: 111341 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3468. Min Act: -0.0002

Data Index: 469290 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3345. Min Act: -0.0002

Data Index: 1343457 (C4 (Web Text))

Max Activating Token Index: 346