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

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

Neuron 3504 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: 2.0617. Min Range: -2.0617

Max Act: 2.0617. Min Act: -0.0000

Data Index: 472011 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.9519. Min Act: -0.0000

Data Index: 971539 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.9182. Min Act: -0.0000

Data Index: 305003 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.8164. Min Act: -0.0000

Data Index: 6191 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 2.0617. Min Range: -2.0617

Max Act: 2.0066. Min Act: -0.0000

Data Index: 1290063 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 2.0617. Min Range: -2.0617

Max Act: 2.0547. Min Act: -0.0000

Data Index: 982105 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.9992. Min Act: -0.0000

Data Index: 5858 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.8788. Min Act: -0.0000

Data Index: 673410 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.9546. Min Act: -0.0000

Data Index: 141676 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.8266. Min Act: -0.0000

Data Index: 1307100 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.8259. Min Act: -0.0000

Data Index: 281958 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.6251. Min Act: -0.0000

Data Index: 210536 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.5859. Min Act: -0.0000

Data Index: 622081 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.6333. Min Act: -0.0000

Data Index: 1222073 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.7329. Min Act: -0.0000

Data Index: 291097 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.7260. Min Act: -0.0000

Data Index: 1319864 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.8007. Min Act: -0.0000

Data Index: 517674 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.5277. Min Act: -0.0000

Data Index: 1146905 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.5975. Min Act: -0.0000

Data Index: 25483 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 2.0617. Min Range: -2.0617

Max Act: 1.6835. Min Act: -0.0000

Data Index: 41457 (C4 (Web Text))

Max Activating Token Index: 1014