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

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

Neuron 5884 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: 0.1934. Min Range: -0.1934

Max Act: 0.1934. Min Act: -0.0001

Data Index: 28156 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1826. Min Act: -0.0001

Data Index: 800284 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1723. Min Act: -0.0001

Data Index: 216645 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1592. Min Act: -0.0001

Data Index: 82047 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1569. Min Act: -0.0001

Data Index: 10338 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1592. Min Act: -0.0001

Data Index: 574634 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1410. Min Act: -0.0001

Data Index: 736769 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1444. Min Act: -0.0001

Data Index: 608178 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1379. Min Act: -0.0001

Data Index: 234561 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1300. Min Act: -0.0001

Data Index: 67779 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1268. Min Act: -0.0001

Data Index: 146925 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1214. Min Act: -0.0001

Data Index: 818997 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1313. Min Act: -0.0001

Data Index: 420405 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1208. Min Act: -0.0001

Data Index: 891997 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1156. Min Act: -0.0001

Data Index: 102627 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1205. Min Act: -0.0001

Data Index: 683222 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1081. Min Act: -0.0001

Data Index: 509665 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1227. Min Act: -0.0001

Data Index: 18203 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1167. Min Act: -0.0001

Data Index: 743419 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1146. Min Act: -0.0001

Data Index: 628958 (C4 (Web Text))

Max Activating Token Index: 173