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

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

Neuron 4216 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5688. Min Act: -0.0000

Data Index: 539707 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5264. Min Act: -0.0000

Data Index: 72511 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4333. Min Act: -0.0000

Data Index: 657673 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1288380 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1261904 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4244. Min Act: -0.0000

Data Index: 378589 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3446. Min Act: -0.0000

Data Index: 446014 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3784. Min Act: -0.0000

Data Index: 745497 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1599361 (Python Code)

Max Activating Token Index: 811

Text #9

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1171407 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3327. Min Act: -0.0000

Data Index: 973604 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3284. Min Act: -0.0000

Data Index: 878560 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1091884 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1387290 (Python Code)

Max Activating Token Index: 661

Text #14

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3342. Min Act: -0.0000

Data Index: 571479 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1563452 (Python Code)

Max Activating Token Index: 1017

Text #16

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3062. Min Act: -0.0000

Data Index: 274396 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1380627 (Python Code)

Max Activating Token Index: 583

Text #18

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.2828. Min Act: -0.0000

Data Index: 317217 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.2898. Min Act: -0.0000

Data Index: 345856 (C4 (Web Text))

Max Activating Token Index: 526