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

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

Neuron 2211 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1803. Min Act: -0.0002

Data Index: 550702 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1527. Min Act: -0.0002

Data Index: 1074137 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1577. Min Act: -0.0002

Data Index: 359320 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1615. Min Act: -0.0002

Data Index: 784298 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1465. Min Act: -0.0002

Data Index: 893991 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1442. Min Act: -0.0002

Data Index: 1082203 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1388. Min Act: -0.0002

Data Index: 1089223 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1387. Min Act: -0.0002

Data Index: 847240 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1412. Min Act: -0.0002

Data Index: 120826 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1362. Min Act: -0.0002

Data Index: 421730 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1358. Min Act: -0.0002

Data Index: 454697 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1074428 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1348. Min Act: -0.0002

Data Index: 341223 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1339. Min Act: -0.0002

Data Index: 935983 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1271. Min Act: -0.0002

Data Index: 39094 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1365. Min Act: -0.0002

Data Index: 97743 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1357. Min Act: -0.0002

Data Index: 520124 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1286. Min Act: -0.0002

Data Index: 1044505 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1139221 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.1803. Min Range: -0.1803

Max Act: 0.1278. Min Act: -0.0002

Data Index: 917363 (C4 (Web Text))

Max Activating Token Index: 53