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

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

Neuron 2806 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1897. Min Act: -0.0000

Data Index: 585785 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1734. Min Act: -0.0001

Data Index: 545655 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1785. Min Act: -0.0000

Data Index: 364881 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1270767 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1157053 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1580. Min Act: -0.0001

Data Index: 961339 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1258491 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1501. Min Act: -0.0000

Data Index: 765803 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1567. Min Act: -0.0001

Data Index: 236876 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1465. Min Act: -0.0000

Data Index: 703508 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1499. Min Act: -0.0000

Data Index: 645113 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1356486 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1484. Min Act: -0.0000

Data Index: 899356 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1533. Min Act: -0.0000

Data Index: 781232 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1434. Min Act: -0.0001

Data Index: 189752 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1415. Min Act: -0.0000

Data Index: 172755 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1420. Min Act: -0.0000

Data Index: 462604 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1368. Min Act: -0.0000

Data Index: 876103 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1401. Min Act: 0.0000

Data Index: 1301592 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1194675 (C4 (Web Text))

Max Activating Token Index: 907