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

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

Neuron 1454 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0564. Min Range: -1.0564

Max Act: 1.0564. Min Act: 0.0000

Data Index: 543764 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.9874. Min Act: -0.0000

Data Index: 10954 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.8533. Min Act: -0.0000

Data Index: 240659 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.8214. Min Act: -0.0000

Data Index: 918378 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7320. Min Act: 0.0000

Data Index: 503048 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7469. Min Act: -0.0000

Data Index: 239538 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7152. Min Act: -0.0000

Data Index: 641330 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1281472 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1209573 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1029743 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7073. Min Act: -0.0000

Data Index: 221830 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6865. Min Act: -0.0000

Data Index: 617212 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6562. Min Act: -0.0000

Data Index: 35779 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1327074 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6435. Min Act: 0.0000

Data Index: 553702 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6526. Min Act: -0.0000

Data Index: 972667 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6276. Min Act: -0.0000

Data Index: 733370 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6432. Min Act: -0.0000

Data Index: 393746 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6660. Min Act: -0.0000

Data Index: 350785 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6149. Min Act: -0.0000

Data Index: 904482 (C4 (Web Text))

Max Activating Token Index: 679