Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 9 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1296. Min Act: -0.0002

Data Index: 1299205 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1268. Min Act: -0.0002

Data Index: 187834 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1246. Min Act: -0.0002

Data Index: 1082792 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1189. Min Act: -0.0002

Data Index: 1037046 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1192. Min Act: -0.0002

Data Index: 534786 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1194. Min Act: -0.0002

Data Index: 217364 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1214. Min Act: -0.0002

Data Index: 194689 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1211. Min Act: -0.0002

Data Index: 1002208 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1199. Min Act: -0.0002

Data Index: 1032871 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1194. Min Act: -0.0002

Data Index: 1293185 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1210. Min Act: -0.0002

Data Index: 980397 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1154. Min Act: -0.0002

Data Index: 242773 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1148. Min Act: -0.0002

Data Index: 308401 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1150. Min Act: -0.0002

Data Index: 64718 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1148. Min Act: -0.0002

Data Index: 1280946 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1168. Min Act: -0.0002

Data Index: 376733 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1149. Min Act: -0.0001

Data Index: 992940 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1146. Min Act: -0.0002

Data Index: 462499 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1151. Min Act: -0.0002

Data Index: 672508 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1139. Min Act: -0.0002

Data Index: 296136 (C4 (Web Text))

Max Activating Token Index: 857