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

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

Neuron 1234 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1410179 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1475489 (Python Code)

Max Activating Token Index: 982

Text #2

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1473078 (Python Code)

Max Activating Token Index: 931

Text #3

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1367869 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1625401 (Python Code)

Max Activating Token Index: 344

Text #5

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1622755 (Python Code)

Max Activating Token Index: 595

Text #6

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1547668 (Python Code)

Max Activating Token Index: 933

Text #7

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1612584 (Python Code)

Max Activating Token Index: 306

Text #8

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1547573 (Python Code)

Max Activating Token Index: 616

Text #9

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1443117 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1642044 (Python Code)

Max Activating Token Index: 685

Text #11

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1417714 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1508173 (Python Code)

Max Activating Token Index: 212

Text #13

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1485893 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1367485 (Python Code)

Max Activating Token Index: 980

Text #15

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1417287 (Python Code)

Max Activating Token Index: 416

Text #16

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1546863 (Python Code)

Max Activating Token Index: 718

Text #17

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1597413 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1546531 (Python Code)

Max Activating Token Index: 422

Text #19

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1531057 (Python Code)

Max Activating Token Index: 763