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

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

Neuron 362 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1598. Min Act: -0.0000

Data Index: 705986 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1640. Min Act: -0.0000

Data Index: 24542 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1677. Min Act: -0.0000

Data Index: 685461 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1561. Min Act: -0.0001

Data Index: 334087 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1497. Min Act: -0.0000

Data Index: 134901 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1402. Min Act: -0.0000

Data Index: 348950 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1470. Min Act: -0.0000

Data Index: 65943 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1259. Min Act: -0.0000

Data Index: 884243 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1283. Min Act: -0.0001

Data Index: 597823 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1297. Min Act: -0.0000

Data Index: 428471 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1388. Min Act: -0.0000

Data Index: 336797 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1199. Min Act: -0.0000

Data Index: 1003670 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1331. Min Act: -0.0000

Data Index: 766497 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1265. Min Act: -0.0000

Data Index: 790614 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1124. Min Act: -0.0000

Data Index: 702578 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1170659 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1374. Min Act: -0.0000

Data Index: 914932 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1213. Min Act: -0.0001

Data Index: 81579 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1171. Min Act: -0.0001

Data Index: 181978 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1113. Min Act: -0.0000

Data Index: 591914 (C4 (Web Text))

Max Activating Token Index: 845