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

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

Neuron 3272 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1201. Min Act: -0.0000

Data Index: 753079 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1181. Min Act: -0.0000

Data Index: 875143 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1009. Min Act: -0.0000

Data Index: 558750 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1038251 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1521221 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1350317 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0975. Min Act: -0.0000

Data Index: 871634 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1214953 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1092261 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0963. Min Act: -0.0000

Data Index: 207086 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0935. Min Act: -0.0000

Data Index: 106342 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1036999 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0895. Min Act: -0.0000

Data Index: 309289 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0825. Min Act: -0.0000

Data Index: 458592 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0878. Min Act: -0.0000

Data Index: 66973 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1099330 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0864. Min Act: -0.0000

Data Index: 253985 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1168905 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0824. Min Act: -0.0000

Data Index: 260577 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0848. Min Act: -0.0000

Data Index: 216829 (C4 (Web Text))

Max Activating Token Index: 376