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

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

Neuron 1403 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0003

Data Index: 209771 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1193007 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1065133 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0301. Min Act: -0.0003

Data Index: 950658 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0283. Min Act: -0.0003

Data Index: 828748 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1322859 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0266. Min Act: -0.0003

Data Index: 671008 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0287. Min Act: -0.0003

Data Index: 322948 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0284. Min Act: -0.0003

Data Index: 292359 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0276. Min Act: -0.0003

Data Index: 396727 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0236. Min Act: -0.0003

Data Index: 920647 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1228218 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1289326 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1302857 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0252. Min Act: -0.0003

Data Index: 607058 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0268. Min Act: -0.0003

Data Index: 384808 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0251. Min Act: -0.0003

Data Index: 959584 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0265. Min Act: -0.0003

Data Index: 930053 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0252. Min Act: -0.0003

Data Index: 649100 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0236. Min Act: -0.0002

Data Index: 410883 (C4 (Web Text))

Max Activating Token Index: 381