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

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

Neuron 802 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.7113. Min Act: -0.0000

Data Index: 273655 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5614. Min Act: -0.0000

Data Index: 215267 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5536. Min Act: -0.0000

Data Index: 914782 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1297905 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5184. Min Act: -0.0000

Data Index: 403783 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5188. Min Act: -0.0000

Data Index: 927398 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4646. Min Act: -0.0000

Data Index: 572149 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4649. Min Act: 0.0000

Data Index: 309136 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4676. Min Act: -0.0000

Data Index: 689210 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4638. Min Act: -0.0000

Data Index: 457121 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4488. Min Act: -0.0000

Data Index: 535307 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4436. Min Act: -0.0000

Data Index: 844339 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1038705 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1201895 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1332656 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1215936 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4272. Min Act: -0.0000

Data Index: 567760 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1168639 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1285867 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4141. Min Act: -0.0000

Data Index: 320939 (C4 (Web Text))

Max Activating Token Index: 76