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

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

Neuron 249 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.6065. Min Act: -0.0000

Data Index: 1307690 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.5762. Min Act: -0.0000

Data Index: 790077 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.4096. Min Act: -0.0000

Data Index: 213472 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3928. Min Act: -0.0000

Data Index: 141840 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3884. Min Act: -0.0000

Data Index: 837568 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.4487. Min Act: -0.0000

Data Index: 214374 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3490. Min Act: -0.0000

Data Index: 1348870 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.4093. Min Act: -0.0000

Data Index: 140451 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3284. Min Act: -0.0000

Data Index: 469371 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2449. Min Act: -0.0000

Data Index: 959983 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1215686 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3142. Min Act: -0.0000

Data Index: 528014 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3104. Min Act: -0.0000

Data Index: 92609 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1229969 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.1973. Min Act: -0.0000

Data Index: 665880 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2663. Min Act: -0.0000

Data Index: 1312897 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2006. Min Act: -0.0000

Data Index: 570197 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2526. Min Act: -0.0000

Data Index: 726385 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.1019. Min Act: -0.0000

Data Index: 626738 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2343. Min Act: -0.0000

Data Index: 1200037 (C4 (Web Text))

Max Activating Token Index: 100