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

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

Neuron 1159 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: 0.9124. Min Range: -0.9124

Max Act: 0.9058. Min Act: -0.0001

Data Index: 1611255 (Python Code)

Max Activating Token Index: 904

Text #1

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.9124. Min Act: -0.0001

Data Index: 1608547 (Python Code)

Max Activating Token Index: 415

Text #2

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.8051. Min Act: -0.0001

Data Index: 1537028 (Python Code)

Max Activating Token Index: 894

Text #3

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.8341. Min Act: -0.0001

Data Index: 1622681 (Python Code)

Max Activating Token Index: 78

Text #4

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7891. Min Act: -0.0001

Data Index: 1452631 (Python Code)

Max Activating Token Index: 491

Text #5

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7711. Min Act: -0.0001

Data Index: 1526250 (Python Code)

Max Activating Token Index: 207

Text #6

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6586. Min Act: -0.0001

Data Index: 1394196 (Python Code)

Max Activating Token Index: 652

Text #7

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6772. Min Act: -0.0001

Data Index: 1574977 (Python Code)

Max Activating Token Index: 609

Text #8

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6839. Min Act: -0.0001

Data Index: 1427746 (Python Code)

Max Activating Token Index: 824

Text #9

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7329. Min Act: -0.0001

Data Index: 1411377 (Python Code)

Max Activating Token Index: 955

Text #10

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6830. Min Act: -0.0001

Data Index: 1617815 (Python Code)

Max Activating Token Index: 675

Text #11

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7167. Min Act: -0.0001

Data Index: 1473108 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7039. Min Act: -0.0001

Data Index: 1558891 (Python Code)

Max Activating Token Index: 953

Text #13

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6783. Min Act: -0.0001

Data Index: 1390580 (Python Code)

Max Activating Token Index: 597

Text #14

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6133. Min Act: -0.0001

Data Index: 1467433 (Python Code)

Max Activating Token Index: 907

Text #15

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6736. Min Act: -0.0001

Data Index: 1479637 (Python Code)

Max Activating Token Index: 468

Text #16

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6742. Min Act: -0.0001

Data Index: 1521408 (Python Code)

Max Activating Token Index: 583

Text #17

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7157. Min Act: -0.0001

Data Index: 1495469 (Python Code)

Max Activating Token Index: 282

Text #18

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6914. Min Act: -0.0001

Data Index: 1561092 (Python Code)

Max Activating Token Index: 803

Text #19

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1530360 (Python Code)

Max Activating Token Index: 883