Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 146 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1658. Min Act: -0.0002

Data Index: 156387 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1455. Min Act: -0.0002

Data Index: 305962 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1531. Min Act: -0.0002

Data Index: 1192191 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1202500 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1408. Min Act: -0.0002

Data Index: 212227 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1241. Min Act: -0.0002

Data Index: 1124693 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1267. Min Act: -0.0002

Data Index: 1222348 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1239. Min Act: -0.0002

Data Index: 344850 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1205. Min Act: -0.0002

Data Index: 566329 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1202. Min Act: -0.0002

Data Index: 299119 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1117. Min Act: -0.0002

Data Index: 736308 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1180. Min Act: -0.0002

Data Index: 829833 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1242. Min Act: -0.0002

Data Index: 528738 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1171. Min Act: -0.0002

Data Index: 619858 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1081. Min Act: -0.0002

Data Index: 142869 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1121. Min Act: -0.0002

Data Index: 696939 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1122. Min Act: -0.0002

Data Index: 356423 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1154. Min Act: -0.0002

Data Index: 18462 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1138. Min Act: -0.0002

Data Index: 244385 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.0929. Min Act: -0.0002

Data Index: 753232 (C4 (Web Text))

Max Activating Token Index: 138