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

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

Neuron 5269 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: 0.9521. Min Range: -0.9521

Max Act: 0.9419. Min Act: -0.0001

Data Index: 1059354 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8802. Min Act: -0.0001

Data Index: 112126 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8734. Min Act: -0.0001

Data Index: 1290853 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.9521. Min Act: -0.0001

Data Index: 464796 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7593. Min Act: -0.0001

Data Index: 998456 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7931. Min Act: -0.0001

Data Index: 1369237 (Python Code)

Max Activating Token Index: 85

Text #6

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8377. Min Act: -0.0001

Data Index: 553408 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6521. Min Act: -0.0001

Data Index: 1131630 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7542. Min Act: -0.0001

Data Index: 667463 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7830. Min Act: -0.0001

Data Index: 75027 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7810. Min Act: -0.0001

Data Index: 198370 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7454. Min Act: -0.0001

Data Index: 1368813 (Python Code)

Max Activating Token Index: 503

Text #12

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7665. Min Act: -0.0001

Data Index: 592751 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7017. Min Act: -0.0001

Data Index: 468855 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7663. Min Act: -0.0001

Data Index: 30684 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7224. Min Act: -0.0001

Data Index: 340236 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7563. Min Act: -0.0001

Data Index: 37584 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7204. Min Act: -0.0001

Data Index: 426888 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7541. Min Act: -0.0001

Data Index: 316315 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7638. Min Act: -0.0001

Data Index: 1539228 (Python Code)

Max Activating Token Index: 117