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

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

Neuron 3791 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.6582. Min Act: -0.0000

Data Index: 435822 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.3100. Min Act: -0.0000

Data Index: 1291826 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.2710. Min Act: -0.0000

Data Index: 186151 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.1678. Min Act: -0.0000

Data Index: 183839 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.1221. Min Act: -0.0000

Data Index: 66473 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.1442. Min Act: -0.0000

Data Index: 44530 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.0376. Min Act: -0.0000

Data Index: 4904 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.0310. Min Act: -0.0000

Data Index: 489192 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.0927. Min Act: -0.0000

Data Index: 1341177 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.0387. Min Act: -0.0000

Data Index: 328933 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1144408 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1174362 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.0243. Min Act: -0.0000

Data Index: 528893 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 1.6582. Min Range: -1.6582

Max Act: 0.9967. Min Act: -0.0000

Data Index: 133774 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.0248. Min Act: -0.0000

Data Index: 882517 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 1.6582. Min Range: -1.6582

Max Act: 0.9695. Min Act: 0.0000

Data Index: 22609 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 1.6582. Min Range: -1.6582

Max Act: 0.9199. Min Act: -0.0000

Data Index: 658829 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 1.6582. Min Range: -1.6582

Max Act: 0.9719. Min Act: -0.0000

Data Index: 958619 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1290654 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 1.6582. Min Range: -1.6582

Max Act: 0.9498. Min Act: -0.0000

Data Index: 805052 (C4 (Web Text))

Max Activating Token Index: 378