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

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

Neuron 306 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4660. Min Range: -4.4660

Max Act: 4.4660. Min Act: -0.0001

Data Index: 650011 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 4.4660. Min Range: -4.4660

Max Act: 4.2482. Min Act: -0.0001

Data Index: 763492 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 4.4660. Min Range: -4.4660

Max Act: 4.1831. Min Act: -0.0001

Data Index: 289269 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.7600. Min Act: -0.0001

Data Index: 636455 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.6486. Min Act: -0.0001

Data Index: 1237430 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.8044. Min Act: -0.0001

Data Index: 1153073 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.3321. Min Act: -0.0001

Data Index: 915566 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.3651. Min Act: -0.0001

Data Index: 259833 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.7699. Min Act: -0.0001

Data Index: 184345 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.2875. Min Act: -0.0001

Data Index: 53487 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.2754. Min Act: -0.0001

Data Index: 771053 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.2340. Min Act: -0.0001

Data Index: 390946 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.1786. Min Act: -0.0001

Data Index: 7556 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.1172. Min Act: -0.0001

Data Index: 1088433 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.0546. Min Act: -0.0001

Data Index: 710860 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.0263. Min Act: -0.0001

Data Index: 345759 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.1634. Min Act: -0.0001

Data Index: 430893 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.0164. Min Act: -0.0001

Data Index: 406448 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.1357. Min Act: -0.0001

Data Index: 999799 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 4.4660. Min Range: -4.4660

Max Act: 3.0450. Min Act: -0.0001

Data Index: 1167570 (C4 (Web Text))

Max Activating Token Index: 513