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

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

Neuron 3479 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0476. Min Act: -0.0001

Data Index: 830422 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0468. Min Act: -0.0001

Data Index: 723491 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0413. Min Act: -0.0001

Data Index: 955642 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0453. Min Act: -0.0001

Data Index: 613504 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0001

Data Index: 843241 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1242736 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0436. Min Act: -0.0001

Data Index: 274398 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0446. Min Act: -0.0001

Data Index: 781477 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0409. Min Act: -0.0001

Data Index: 754024 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1170755 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1129716 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0407. Min Act: -0.0001

Data Index: 155778 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0412. Min Act: -0.0001

Data Index: 340712 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1197787 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1619798 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0386. Min Act: -0.0002

Data Index: 798491 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0386. Min Act: -0.0001

Data Index: 802074 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0374. Min Act: -0.0001

Data Index: 486214 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0367. Min Act: -0.0001

Data Index: 904194 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1019565 (C4 (Web Text))

Max Activating Token Index: 410