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

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

Neuron 2500 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: 0.2044. Min Range: -0.2044

Max Act: 0.2044. Min Act: -0.0002

Data Index: 1097935 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1668. Min Act: -0.0002

Data Index: 813294 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1649. Min Act: -0.0002

Data Index: 604060 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1458. Min Act: -0.0002

Data Index: 1341692 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1451. Min Act: -0.0002

Data Index: 931104 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1427. Min Act: -0.0002

Data Index: 1086662 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1390. Min Act: -0.0002

Data Index: 122769 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1389. Min Act: -0.0002

Data Index: 1083378 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1377. Min Act: -0.0002

Data Index: 118285 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1367. Min Act: -0.0002

Data Index: 1083948 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1357. Min Act: -0.0002

Data Index: 964629 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1361. Min Act: -0.0002

Data Index: 282178 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1327. Min Act: -0.0002

Data Index: 140237 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1320. Min Act: -0.0002

Data Index: 1251179 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1374. Min Act: -0.0002

Data Index: 280402 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1339. Min Act: -0.0002

Data Index: 1293862 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1325. Min Act: -0.0002

Data Index: 42390 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1280. Min Act: -0.0002

Data Index: 61714 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1229. Min Act: -0.0002

Data Index: 772887 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1223. Min Act: -0.0002

Data Index: 556525 (C4 (Web Text))

Max Activating Token Index: 724