Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 510 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.8211. Min Act: 0.0000

Data Index: 1150421 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7514. Min Act: -0.0000

Data Index: 806068 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7532. Min Act: -0.0000

Data Index: 399245 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6931. Min Act: -0.0000

Data Index: 529542 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6559. Min Act: -0.0000

Data Index: 561577 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6703. Min Act: 0.0001

Data Index: 977667 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6049. Min Act: -0.0000

Data Index: 664210 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6148. Min Act: 0.0000

Data Index: 1025450 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1163899 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5755. Min Act: -0.0000

Data Index: 76951 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5732. Min Act: -0.0000

Data Index: 965116 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5514. Min Act: -0.0000

Data Index: 139088 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5469. Min Act: 0.0000

Data Index: 70457 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5329. Min Act: -0.0000

Data Index: 350264 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5338. Min Act: 0.0000

Data Index: 157222 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5256. Min Act: 0.0001

Data Index: 1219040 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5285. Min Act: -0.0000

Data Index: 568535 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5338. Min Act: -0.0000

Data Index: 608761 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5018. Min Act: -0.0000

Data Index: 224741 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.4987. Min Act: 0.0001

Data Index: 423386 (C4 (Web Text))

Max Activating Token Index: 514