Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4451 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3656. Min Act: -0.0000

Data Index: 382647 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3718. Min Act: -0.0000

Data Index: 756275 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3736. Min Act: -0.0000

Data Index: 526602 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1100773 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1297529 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3360. Min Act: -0.0000

Data Index: 315152 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1570445 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3491. Min Act: -0.0000

Data Index: 131140 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3553. Min Act: -0.0000

Data Index: 974804 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3291. Min Act: -0.0000

Data Index: 375104 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3280. Min Act: -0.0000

Data Index: 835136 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3500. Min Act: -0.0000

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3496. Min Act: -0.0000

Data Index: 209096 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3373. Min Act: -0.0000

Data Index: 388392 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3332. Min Act: -0.0000

Data Index: 81942 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1237889 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3322. Min Act: -0.0000

Data Index: 751333 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3437. Min Act: -0.0000

Data Index: 531602 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1267033 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3289. Min Act: -0.0000

Data Index: 297930 (C4 (Web Text))

Max Activating Token Index: 558