Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 956 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0250. Min Act: -0.0005

Data Index: 1305038 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0006

Data Index: 947797 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0006

Data Index: 1235772 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1069132 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0253. Min Act: -0.0005

Data Index: 1127079 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0251. Min Act: -0.0006

Data Index: 806091 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1383577 (Python Code)

Max Activating Token Index: 635

Text #7

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0239. Min Act: -0.0006

Data Index: 942159 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0250. Min Act: -0.0006

Data Index: 835647 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0244. Min Act: -0.0005

Data Index: 645631 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0248. Min Act: -0.0006

Data Index: 148002 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1390350 (Python Code)

Max Activating Token Index: 908

Text #12

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1623098 (Python Code)

Max Activating Token Index: 951

Text #13

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0244. Min Act: -0.0005

Data Index: 663200 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1508390 (Python Code)

Max Activating Token Index: 959

Text #15

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1422434 (Python Code)

Max Activating Token Index: 456

Text #16

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0241. Min Act: -0.0006

Data Index: 299995 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0241. Min Act: -0.0006

Data Index: 824239 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0237. Min Act: -0.0006

Data Index: 203708 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0245. Min Act: -0.0006

Data Index: 584642 (C4 (Web Text))

Max Activating Token Index: 826