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

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

Neuron 2186 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1612613 (Python Code)

Max Activating Token Index: 137

Text #1

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1564895 (Python Code)

Max Activating Token Index: 310

Text #2

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1434688 (Python Code)

Max Activating Token Index: 242

Text #3

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1406327 (Python Code)

Max Activating Token Index: 350

Text #4

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1501775 (Python Code)

Max Activating Token Index: 668

Text #5

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1483185 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1402547 (Python Code)

Max Activating Token Index: 859

Text #7

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1438240 (Python Code)

Max Activating Token Index: 270

Text #8

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1606693 (Python Code)

Max Activating Token Index: 553

Text #9

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1376045 (Python Code)

Max Activating Token Index: 197

Text #10

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1617486 (Python Code)

Max Activating Token Index: 413

Text #11

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1595766 (Python Code)

Max Activating Token Index: 498

Text #12

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1549419 (Python Code)

Max Activating Token Index: 671

Text #13

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1482524 (Python Code)

Max Activating Token Index: 826

Text #14

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1601685 (Python Code)

Max Activating Token Index: 160

Text #15

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1408137 (Python Code)

Max Activating Token Index: 377

Text #16

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1392968 (Python Code)

Max Activating Token Index: 886

Text #17

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1443234 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1461149 (Python Code)

Max Activating Token Index: 597

Text #19

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1605993 (Python Code)

Max Activating Token Index: 878