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

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

Neuron 950 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1589. Min Range: -1.1589

Max Act: 1.1589. Min Act: -0.0001

Data Index: 223395 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 1.1589. Min Range: -1.1589

Max Act: 1.1349. Min Act: -0.0001

Data Index: 1108219 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 1.1589. Min Range: -1.1589

Max Act: 1.0393. Min Act: -0.0001

Data Index: 1157819 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 1.1589. Min Range: -1.1589

Max Act: 1.0020. Min Act: -0.0001

Data Index: 842206 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9358. Min Act: -0.0001

Data Index: 452899 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9365. Min Act: -0.0001

Data Index: 1251631 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8629. Min Act: -0.0001

Data Index: 865577 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.9005. Min Act: -0.0001

Data Index: 369683 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8934. Min Act: -0.0001

Data Index: 1305989 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8574. Min Act: -0.0001

Data Index: 1126751 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8255. Min Act: -0.0001

Data Index: 1345516 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8280. Min Act: -0.0001

Data Index: 1117524 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.7970. Min Act: -0.0001

Data Index: 1018622 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8447. Min Act: -0.0001

Data Index: 1281628 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8209. Min Act: -0.0001

Data Index: 766615 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8416. Min Act: -0.0001

Data Index: 1281666 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8384. Min Act: -0.0001

Data Index: 468582 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8005. Min Act: -0.0001

Data Index: 821894 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8539. Min Act: -0.0001

Data Index: 925983 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 1.1589. Min Range: -1.1589

Max Act: 0.8723. Min Act: -0.0001

Data Index: 1111706 (C4 (Web Text))

Max Activating Token Index: 712