Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2420 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1876. Min Act: -0.0000

Data Index: 956094 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1727. Min Act: -0.0000

Data Index: 138578 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1560. Min Act: -0.0000

Data Index: 236979 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1566. Min Act: -0.0000

Data Index: 937351 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1293. Min Act: -0.0000

Data Index: 466807 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1372. Min Act: -0.0000

Data Index: 494249 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1345. Min Act: -0.0000

Data Index: 584395 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1131984 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1274. Min Act: -0.0000

Data Index: 924208 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1283. Min Act: -0.0000

Data Index: 266049 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1227. Min Act: -0.0000

Data Index: 559010 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1270. Min Act: -0.0000

Data Index: 639186 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1186847 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1325990 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1215. Min Act: -0.0000

Data Index: 80963 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1175. Min Act: -0.0000

Data Index: 934319 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1266. Min Act: -0.0000

Data Index: 392826 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1455859 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1166. Min Act: -0.0000

Data Index: 793572 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1108. Min Act: -0.0000

Data Index: 934494 (C4 (Web Text))

Max Activating Token Index: 943