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

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

Neuron 676 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1355701 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1295. Min Act: -0.0000

Data Index: 187447 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1382. Min Act: -0.0000

Data Index: 790711 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1332. Min Act: -0.0000

Data Index: 588571 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1328. Min Act: -0.0000

Data Index: 306927 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1222. Min Act: -0.0000

Data Index: 522780 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1301. Min Act: -0.0000

Data Index: 276149 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1182. Min Act: -0.0000

Data Index: 249892 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1329401 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1275. Min Act: -0.0000

Data Index: 837570 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1278. Min Act: -0.0000

Data Index: 296607 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1287450 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1131. Min Act: -0.0000

Data Index: 575950 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1328326 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1108. Min Act: -0.0000

Data Index: 975203 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1107. Min Act: -0.0000

Data Index: 568606 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1084. Min Act: -0.0000

Data Index: 92735 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1071. Min Act: -0.0000

Data Index: 672098 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1028. Min Act: -0.0000

Data Index: 29971 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1031. Min Act: -0.0000

Data Index: 185428 (C4 (Web Text))

Max Activating Token Index: 686