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

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

Neuron 4210 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: 2.4658. Min Range: -2.4658

Max Act: 2.4658. Min Act: -0.0000

Data Index: 1461367 (Python Code)

Max Activating Token Index: 509

Text #1

Max Range: 2.4658. Min Range: -2.4658

Max Act: 2.3627. Min Act: -0.0000

Data Index: 1408479 (Python Code)

Max Activating Token Index: 388

Text #2

Max Range: 2.4658. Min Range: -2.4658

Max Act: 2.2678. Min Act: -0.0000

Data Index: 1618340 (Python Code)

Max Activating Token Index: 596

Text #3

Max Range: 2.4658. Min Range: -2.4658

Max Act: 2.0446. Min Act: -0.0000

Data Index: 1370857 (Python Code)

Max Activating Token Index: 581

Text #4

Max Range: 2.4658. Min Range: -2.4658

Max Act: 2.0455. Min Act: -0.0000

Data Index: 1478695 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 2.4658. Min Range: -2.4658

Max Act: 2.1570. Min Act: -0.0000

Data Index: 1556440 (Python Code)

Max Activating Token Index: 181

Text #6

Max Range: 2.4658. Min Range: -2.4658

Max Act: 2.0014. Min Act: -0.0000

Data Index: 1574731 (Python Code)

Max Activating Token Index: 906

Text #7

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.9290. Min Act: -0.0000

Data Index: 1460308 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.8847. Min Act: -0.0000

Data Index: 1630169 (Python Code)

Max Activating Token Index: 627

Text #9

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.7915. Min Act: -0.0000

Data Index: 1505378 (Python Code)

Max Activating Token Index: 804

Text #10

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.7833. Min Act: -0.0000

Data Index: 1376486 (Python Code)

Max Activating Token Index: 353

Text #11

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.6300. Min Act: -0.0000

Data Index: 1061192 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.6678. Min Act: -0.0000

Data Index: 1383670 (Python Code)

Max Activating Token Index: 937

Text #13

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.5428. Min Act: -0.0000

Data Index: 1585859 (Python Code)

Max Activating Token Index: 223

Text #14

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.8406. Min Act: -0.0000

Data Index: 1520740 (Python Code)

Max Activating Token Index: 119

Text #15

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.7282. Min Act: -0.0000

Data Index: 1557981 (Python Code)

Max Activating Token Index: 334

Text #16

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.5907. Min Act: -0.0000

Data Index: 1647872 (Python Code)

Max Activating Token Index: 605

Text #17

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.6135. Min Act: -0.0000

Data Index: 1623472 (Python Code)

Max Activating Token Index: 860

Text #18

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.5167. Min Act: -0.0000

Data Index: 1438284 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 2.4658. Min Range: -2.4658

Max Act: 1.6007. Min Act: -0.0000

Data Index: 1428020 (Python Code)

Max Activating Token Index: 217