Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1465 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0768. Min Act: -0.0003

Data Index: 521093 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0701. Min Act: -0.0003

Data Index: 349597 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0627. Min Act: -0.0003

Data Index: 1231738 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0661. Min Act: -0.0003

Data Index: 133381 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0563. Min Act: -0.0003

Data Index: 501399 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0667. Min Act: -0.0003

Data Index: 430573 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1264731 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0564. Min Act: -0.0003

Data Index: 343364 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0560. Min Act: -0.0003

Data Index: 46735 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0590. Min Act: -0.0003

Data Index: 209760 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0513. Min Act: -0.0003

Data Index: 693218 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0546. Min Act: -0.0003

Data Index: 407817 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0562. Min Act: -0.0003

Data Index: 924580 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0552. Min Act: -0.0003

Data Index: 304611 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1186002 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0510. Min Act: -0.0003

Data Index: 173715 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0498. Min Act: -0.0003

Data Index: 956721 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1097416 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0522. Min Act: -0.0003

Data Index: 49319 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0562. Min Act: -0.0003

Data Index: 189603 (C4 (Web Text))

Max Activating Token Index: 658