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

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

Neuron 2036 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1528. Min Act: -0.0002

Data Index: 54287 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1475. Min Act: -0.0002

Data Index: 1318901 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1458. Min Act: -0.0002

Data Index: 665590 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1369. Min Act: -0.0002

Data Index: 1271626 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1375. Min Act: -0.0002

Data Index: 1202236 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1368. Min Act: -0.0002

Data Index: 542066 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1318. Min Act: -0.0002

Data Index: 807946 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1311. Min Act: -0.0002

Data Index: 1037052 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1255. Min Act: -0.0002

Data Index: 117034 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1223. Min Act: -0.0002

Data Index: 800944 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1222. Min Act: -0.0002

Data Index: 186469 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1186159 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1218. Min Act: -0.0002

Data Index: 1261561 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1045318 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1210. Min Act: -0.0002

Data Index: 246997 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1258. Min Act: -0.0002

Data Index: 627167 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1210. Min Act: -0.0002

Data Index: 886450 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1212. Min Act: -0.0002

Data Index: 399813 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1211. Min Act: -0.0002

Data Index: 584706 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1246. Min Act: -0.0002

Data Index: 414940 (C4 (Web Text))

Max Activating Token Index: 267