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

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

Neuron 570 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2233. Min Act: -0.0000

Data Index: 449041 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2156. Min Act: -0.0000

Data Index: 558536 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1818. Min Act: -0.0000

Data Index: 772213 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1522. Min Act: -0.0000

Data Index: 229644 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1000238 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1531. Min Act: -0.0000

Data Index: 896758 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1439. Min Act: -0.0000

Data Index: 544548 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1661. Min Act: -0.0000

Data Index: 541658 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1553. Min Act: -0.0000

Data Index: 186256 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1692. Min Act: -0.0000

Data Index: 441198 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1290946 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1617. Min Act: -0.0000

Data Index: 316399 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1503. Min Act: -0.0000

Data Index: 828517 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1528. Min Act: -0.0000

Data Index: 190136 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1092289 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1584. Min Act: -0.0000

Data Index: 2558 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1514. Min Act: -0.0000

Data Index: 627078 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1440. Min Act: -0.0000

Data Index: 127775 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1583. Min Act: -0.0000

Data Index: 947521 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1045410 (C4 (Web Text))

Max Activating Token Index: 356