Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1269 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1908. Min Act: -0.0000

Data Index: 511865 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1112795 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1600. Min Act: -0.0000

Data Index: 481372 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1573. Min Act: -0.0000

Data Index: 469064 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1407. Min Act: -0.0000

Data Index: 993129 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1402. Min Act: -0.0000

Data Index: 286460 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1181. Min Act: -0.0000

Data Index: 926663 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1377. Min Act: 0.0000

Data Index: 412855 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1159322 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1089858 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1211. Min Act: -0.0000

Data Index: 830151 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1067569 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1214. Min Act: -0.0000

Data Index: 309106 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1244572 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1416832 (Python Code)

Max Activating Token Index: 605

Text #15

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1344113 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1154. Min Act: -0.0000

Data Index: 797322 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1502807 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1118. Min Act: -0.0000

Data Index: 667951 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1326158 (C4 (Web Text))

Max Activating Token Index: 724