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

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

Neuron 3103 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1476829 (Python Code)

Max Activating Token Index: 329

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0224. Min Act: -0.0003

Data Index: 289961 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1488948 (Python Code)

Max Activating Token Index: 846

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1466810 (Python Code)

Max Activating Token Index: 900

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0203. Min Act: -0.0003

Data Index: 746677 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0216. Min Act: -0.0003

Data Index: 803991 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1520813 (Python Code)

Max Activating Token Index: 253

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0217. Min Act: -0.0003

Data Index: 1134653 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1632373 (Python Code)

Max Activating Token Index: 734

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1615684 (Python Code)

Max Activating Token Index: 880

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1649228 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1486934 (Python Code)

Max Activating Token Index: 750

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0207. Min Act: -0.0003

Data Index: 127007 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1407735 (Python Code)

Max Activating Token Index: 559

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1540282 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1549772 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0212. Min Act: -0.0004

Data Index: 1521995 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1327388 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1562692 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0198. Min Act: -0.0003

Data Index: 295535 (C4 (Web Text))

Max Activating Token Index: 592