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

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

Neuron 1604 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1687. Min Act: -0.0001

Data Index: 862997 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1281786 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1283. Min Act: -0.0001

Data Index: 667025 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1388. Min Act: -0.0001

Data Index: 305495 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1449. Min Act: -0.0001

Data Index: 797543 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1249. Min Act: -0.0001

Data Index: 908655 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1099528 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1244. Min Act: -0.0001

Data Index: 865172 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1203. Min Act: -0.0001

Data Index: 76895 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1264. Min Act: -0.0001

Data Index: 799257 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1248. Min Act: -0.0001

Data Index: 439284 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1127. Min Act: -0.0001

Data Index: 613170 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1196. Min Act: -0.0002

Data Index: 1241998 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1197. Min Act: -0.0001

Data Index: 704550 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1051047 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1204. Min Act: -0.0002

Data Index: 457062 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1299617 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1096. Min Act: -0.0001

Data Index: 699174 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1014. Min Act: -0.0001

Data Index: 409944 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.1687. Min Range: -0.1687

Max Act: 0.1035. Min Act: -0.0002

Data Index: 25625 (C4 (Web Text))

Max Activating Token Index: 267