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

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

Neuron 5441 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1148224 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0508. Min Act: -0.0002

Data Index: 699883 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0421. Min Act: -0.0002

Data Index: 766455 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0525. Min Act: -0.0002

Data Index: 139604 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1423897 (Python Code)

Max Activating Token Index: 514

Text #5

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1079760 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1051260 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0455. Min Act: -0.0002

Data Index: 859262 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1509571 (Python Code)

Max Activating Token Index: 757

Text #9

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1085472 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1035579 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0414. Min Act: -0.0002

Data Index: 822218 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1496537 (Python Code)

Max Activating Token Index: 406

Text #13

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0366. Min Act: -0.0002

Data Index: 665946 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0362. Min Act: -0.0002

Data Index: 125108 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1036147 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0377. Min Act: -0.0002

Data Index: 465347 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0401. Min Act: -0.0002

Data Index: 985466 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1393416 (Python Code)

Max Activating Token Index: 649

Text #19

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1221129 (C4 (Web Text))

Max Activating Token Index: 774