Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3643 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1882. Min Act: -0.0002

Data Index: 740377 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1188872 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1297635 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1768. Min Act: -0.0001

Data Index: 480038 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1684. Min Act: -0.0001

Data Index: 395228 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1192902 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1671. Min Act: -0.0001

Data Index: 371279 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1666. Min Act: -0.0001

Data Index: 627040 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1595. Min Act: -0.0002

Data Index: 1266725 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1640. Min Act: -0.0001

Data Index: 671909 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1570. Min Act: -0.0001

Data Index: 667840 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1626. Min Act: -0.0001

Data Index: 1229612 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1604. Min Act: -0.0001

Data Index: 594892 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1601. Min Act: -0.0002

Data Index: 1177008 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1653. Min Act: -0.0002

Data Index: 1277888 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1575. Min Act: -0.0001

Data Index: 583163 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1266184 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1538. Min Act: -0.0002

Data Index: 926406 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1537. Min Act: -0.0002

Data Index: 173289 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1647. Min Act: -0.0001

Data Index: 912179 (C4 (Web Text))

Max Activating Token Index: 831