Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 955 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.2070. Min Act: -0.0001

Data Index: 371021 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1692. Min Act: -0.0001

Data Index: 971483 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1669. Min Act: -0.0001

Data Index: 1232582 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1690. Min Act: -0.0001

Data Index: 316445 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1486. Min Act: -0.0001

Data Index: 328773 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1583. Min Act: -0.0001

Data Index: 859144 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1426. Min Act: -0.0001

Data Index: 789462 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1420. Min Act: -0.0001

Data Index: 31113 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1312754 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1122340 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1444. Min Act: -0.0001

Data Index: 132832 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1368. Min Act: -0.0001

Data Index: 739262 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1255186 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1288. Min Act: -0.0001

Data Index: 236673 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1269. Min Act: -0.0001

Data Index: 477434 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1343. Min Act: -0.0001

Data Index: 868748 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1338. Min Act: -0.0001

Data Index: 723572 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1328. Min Act: -0.0001

Data Index: 559975 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1373. Min Act: -0.0001

Data Index: 862768 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1226825 (C4 (Web Text))

Max Activating Token Index: 1003