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

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

Neuron 4171 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.8619. Min Act: -0.0000

Data Index: 124692 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.8649. Min Act: -0.0000

Data Index: 1000238 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.7438. Min Act: -0.0001

Data Index: 176008 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.8181. Min Act: -0.0001

Data Index: 533437 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.9805. Min Act: -0.0000

Data Index: 1245215 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.7024. Min Act: -0.0000

Data Index: 836799 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.5007. Min Act: -0.0000

Data Index: 909611 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.4851. Min Act: -0.0000

Data Index: 414190 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.3102. Min Act: -0.0000

Data Index: 1299617 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.4598. Min Act: -0.0001

Data Index: 57430 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.6242. Min Act: -0.0000

Data Index: 849544 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.5002. Min Act: -0.0000

Data Index: 766715 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.3764. Min Act: -0.0000

Data Index: 229644 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.4729. Min Act: -0.0000

Data Index: 743100 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.4682. Min Act: -0.0000

Data Index: 999444 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.1137. Min Act: -0.0000

Data Index: 355016 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.4383. Min Act: -0.0000

Data Index: 1089720 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.1293. Min Act: -0.0000

Data Index: 1321807 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 4.9805. Min Range: -4.9805

Max Act: 3.9069. Min Act: -0.0000

Data Index: 216988 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 4.9805. Min Range: -4.9805

Max Act: 4.4110. Min Act: -0.0000

Data Index: 908188 (C4 (Web Text))

Max Activating Token Index: 124