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

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

Neuron 3202 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: 0.1819. Min Range: -0.1819

Max Act: 0.1819. Min Act: -0.0002

Data Index: 809274 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1745. Min Act: -0.0002

Data Index: 1075710 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1680. Min Act: -0.0002

Data Index: 182424 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1680. Min Act: -0.0002

Data Index: 213749 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1558. Min Act: -0.0002

Data Index: 451144 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1455. Min Act: -0.0002

Data Index: 1312475 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1555. Min Act: -0.0002

Data Index: 201619 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1476. Min Act: -0.0002

Data Index: 280757 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1449. Min Act: -0.0002

Data Index: 807023 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1308. Min Act: -0.0002

Data Index: 980931 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1434. Min Act: -0.0002

Data Index: 644879 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1343. Min Act: -0.0002

Data Index: 504983 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1389. Min Act: -0.0002

Data Index: 669219 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1349. Min Act: -0.0002

Data Index: 5869 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1344. Min Act: -0.0002

Data Index: 1133413 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1326. Min Act: -0.0002

Data Index: 897472 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1346. Min Act: -0.0002

Data Index: 1256314 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1307. Min Act: -0.0002

Data Index: 280397 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1295. Min Act: -0.0001

Data Index: 945752 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1291. Min Act: -0.0002

Data Index: 887748 (C4 (Web Text))

Max Activating Token Index: 965