Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2507 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1141788 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1338. Min Act: -0.0001

Data Index: 789666 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1283902 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1265. Min Act: -0.0001

Data Index: 456143 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1089123 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1244. Min Act: -0.0001

Data Index: 566953 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1240. Min Act: -0.0001

Data Index: 289135 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1218. Min Act: -0.0001

Data Index: 864546 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1226. Min Act: -0.0001

Data Index: 975846 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1272. Min Act: -0.0001

Data Index: 1046659 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1219. Min Act: -0.0001

Data Index: 826441 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1036948 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1137. Min Act: -0.0001

Data Index: 212033 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1332761 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1094. Min Act: -0.0001

Data Index: 769437 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1001334 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1038. Min Act: -0.0001

Data Index: 201413 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1136972 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1067. Min Act: -0.0001

Data Index: 266595 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1343381 (C4 (Web Text))

Max Activating Token Index: 772