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

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

Neuron 1700 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.2771. Min Act: -0.0001

Data Index: 340689 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.2627. Min Act: -0.0001

Data Index: 1274646 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.3079. Min Act: -0.0001

Data Index: 1322801 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.2162. Min Act: -0.0001

Data Index: 18424 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1681. Min Act: -0.0001

Data Index: 461821 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1792. Min Act: -0.0001

Data Index: 74754 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1471. Min Act: -0.0001

Data Index: 112109 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1945. Min Act: -0.0001

Data Index: 507081 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1651. Min Act: -0.0001

Data Index: 522730 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1376. Min Act: -0.0000

Data Index: 725202 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1568. Min Act: -0.0001

Data Index: 245342 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.0624. Min Act: -0.0001

Data Index: 1193497 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.0586. Min Act: -0.0001

Data Index: 907274 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.0926. Min Act: -0.0001

Data Index: 16932 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.0635. Min Act: -0.0001

Data Index: 999660 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.0580. Min Act: -0.0001

Data Index: 461426 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1048. Min Act: -0.0001

Data Index: 1234522 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 1.3079. Min Range: -1.3079

Max Act: 0.9995. Min Act: -0.0001

Data Index: 1037080 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1191. Min Act: -0.0001

Data Index: 1337030 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.0497. Min Act: -0.0001

Data Index: 327303 (C4 (Web Text))

Max Activating Token Index: 139