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

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

Neuron 1713 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0398. Min Range: -1.0398

Max Act: 1.0398. Min Act: -0.0001

Data Index: 1518809 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8511. Min Act: -0.0001

Data Index: 1376533 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8425. Min Act: -0.0001

Data Index: 1527285 (Python Code)

Max Activating Token Index: 281

Text #3

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7319. Min Act: -0.0001

Data Index: 1491481 (Python Code)

Max Activating Token Index: 665

Text #4

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7895. Min Act: -0.0001

Data Index: 1419176 (Python Code)

Max Activating Token Index: 737

Text #5

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7866. Min Act: -0.0001

Data Index: 1606655 (Python Code)

Max Activating Token Index: 721

Text #6

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7787. Min Act: -0.0001

Data Index: 1582174 (Python Code)

Max Activating Token Index: 353

Text #7

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7971. Min Act: -0.0001

Data Index: 1465182 (Python Code)

Max Activating Token Index: 858

Text #8

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8212. Min Act: -0.0001

Data Index: 1422850 (Python Code)

Max Activating Token Index: 539

Text #9

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7638. Min Act: -0.0001

Data Index: 1468015 (Python Code)

Max Activating Token Index: 405

Text #10

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8092. Min Act: -0.0001

Data Index: 1386767 (Python Code)

Max Activating Token Index: 339

Text #11

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7503. Min Act: -0.0001

Data Index: 1492638 (Python Code)

Max Activating Token Index: 473

Text #12

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7737. Min Act: -0.0001

Data Index: 1528906 (Python Code)

Max Activating Token Index: 212

Text #13

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7476. Min Act: -0.0001

Data Index: 1385966 (Python Code)

Max Activating Token Index: 355

Text #14

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7370. Min Act: -0.0001

Data Index: 1583823 (Python Code)

Max Activating Token Index: 787

Text #15

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7882. Min Act: -0.0001

Data Index: 1428145 (Python Code)

Max Activating Token Index: 799

Text #16

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7632. Min Act: -0.0001

Data Index: 1613916 (Python Code)

Max Activating Token Index: 399

Text #17

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7341. Min Act: -0.0001

Data Index: 1445209 (Python Code)

Max Activating Token Index: 745

Text #18

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7754. Min Act: -0.0001

Data Index: 1627154 (Python Code)

Max Activating Token Index: 462

Text #19

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7474. Min Act: -0.0001

Data Index: 1376637 (Python Code)

Max Activating Token Index: 270