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

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

Neuron 397 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0505. Min Range: -1.0505

Max Act: 1.0505. Min Act: -0.0000

Data Index: 809877 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9479. Min Act: -0.0000

Data Index: 12609 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 1.0505. Min Range: -1.0505

Max Act: 1.0223. Min Act: -0.0000

Data Index: 858356 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9240. Min Act: -0.0000

Data Index: 466120 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9702. Min Act: -0.0000

Data Index: 481915 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8737. Min Act: -0.0000

Data Index: 537522 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9114. Min Act: -0.0000

Data Index: 166891 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9293. Min Act: -0.0000

Data Index: 393963 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9224. Min Act: -0.0000

Data Index: 757130 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9634. Min Act: -0.0000

Data Index: 786165 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1308510 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9048. Min Act: -0.0000

Data Index: 507126 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9002. Min Act: -0.0000

Data Index: 764041 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8874. Min Act: -0.0000

Data Index: 291233 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9337. Min Act: -0.0000

Data Index: 156834 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9014. Min Act: -0.0000

Data Index: 847950 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8509. Min Act: -0.0000

Data Index: 53904 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9053. Min Act: -0.0000

Data Index: 732017 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1060696 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8779. Min Act: -0.0000

Data Index: 302340 (C4 (Web Text))

Max Activating Token Index: 640