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

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

Neuron 5257 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4243. Min Range: -8.4243

Max Act: 8.4243. Min Act: -0.0000

Data Index: 5 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 8.4243. Min Range: -8.4243

Max Act: 8.0971. Min Act: -0.0000

Data Index: 1018953 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 8.4243. Min Range: -8.4243

Max Act: 6.3031. Min Act: -0.0000

Data Index: 719842 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 8.4243. Min Range: -8.4243

Max Act: 4.6793. Min Act: -0.0000

Data Index: 1219065 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 8.4243. Min Range: -8.4243

Max Act: 4.0476. Min Act: -0.0000

Data Index: 663149 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 8.4243. Min Range: -8.4243

Max Act: 3.5594. Min Act: -0.0000

Data Index: 997660 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 8.4243. Min Range: -8.4243

Max Act: 4.3471. Min Act: -0.0000

Data Index: 743251 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 8.4243. Min Range: -8.4243

Max Act: 4.1044. Min Act: -0.0000

Data Index: 1160532 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 8.4243. Min Range: -8.4243

Max Act: 4.3991. Min Act: -0.0000

Data Index: 1087986 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 8.4243. Min Range: -8.4243

Max Act: 4.3875. Min Act: -0.0000

Data Index: 672220 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 8.4243. Min Range: -8.4243

Max Act: 3.9707. Min Act: -0.0000

Data Index: 1154586 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 8.4243. Min Range: -8.4243

Max Act: 3.9506. Min Act: -0.0000

Data Index: 372599 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 8.4243. Min Range: -8.4243

Max Act: 4.0611. Min Act: -0.0000

Data Index: 1257688 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 8.4243. Min Range: -8.4243

Max Act: 3.9641. Min Act: -0.0000

Data Index: 818950 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 8.4243. Min Range: -8.4243

Max Act: 3.7467. Min Act: -0.0000

Data Index: 1045559 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 8.4243. Min Range: -8.4243

Max Act: 3.7496. Min Act: -0.0000

Data Index: 841227 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 8.4243. Min Range: -8.4243

Max Act: 3.9194. Min Act: -0.0000

Data Index: 1173197 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 8.4243. Min Range: -8.4243

Max Act: 3.2310. Min Act: -0.0000

Data Index: 1099815 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 8.4243. Min Range: -8.4243

Max Act: 3.5466. Min Act: -0.0000

Data Index: 496865 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 8.4243. Min Range: -8.4243

Max Act: 3.8574. Min Act: -0.0000

Data Index: 282950 (C4 (Web Text))

Max Activating Token Index: 282