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

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

Neuron 69 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1881. Min Act: -0.0000

Data Index: 429452 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1477. Min Act: -0.0000

Data Index: 782004 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1534. Min Act: -0.0000

Data Index: 566401 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1432. Min Act: -0.0000

Data Index: 81942 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1266869 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1389. Min Act: -0.0000

Data Index: 495461 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1322. Min Act: -0.0000

Data Index: 309237 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1237. Min Act: -0.0000

Data Index: 863695 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1045502 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1129103 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1190. Min Act: -0.0000

Data Index: 410346 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1205440 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1131. Min Act: -0.0000

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1209. Min Act: -0.0000

Data Index: 109083 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1246. Min Act: -0.0000

Data Index: 445886 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1178. Min Act: -0.0000

Data Index: 248221 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1082. Min Act: -0.0000

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1156. Min Act: -0.0000

Data Index: 137434 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1128. Min Act: -0.0000

Data Index: 863278 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1157. Min Act: -0.0000

Data Index: 871495 (C4 (Web Text))

Max Activating Token Index: 564