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

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

Neuron 4421 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: 3.2996. Min Range: -3.2996

Max Act: 3.1763. Min Act: -0.0000

Data Index: 739279 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 3.2996. Min Range: -3.2996

Max Act: 3.1761. Min Act: -0.0000

Data Index: 1138070 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 3.2996. Min Range: -3.2996

Max Act: 3.2996. Min Act: -0.0000

Data Index: 239700 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 3.2996. Min Range: -3.2996

Max Act: 3.0448. Min Act: -0.0000

Data Index: 939632 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.9891. Min Act: -0.0001

Data Index: 857212 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.9714. Min Act: -0.0001

Data Index: 1079032 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.9047. Min Act: -0.0001

Data Index: 1035810 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.6622. Min Act: -0.0001

Data Index: 161797 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.9941. Min Act: -0.0001

Data Index: 1098445 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.6305. Min Act: -0.0001

Data Index: 912954 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.7741. Min Act: -0.0001

Data Index: 1141255 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.5447. Min Act: -0.0001

Data Index: 713580 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.5200. Min Act: -0.0001

Data Index: 472741 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.7567. Min Act: -0.0000

Data Index: 153654 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.7388. Min Act: -0.0001

Data Index: 251905 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.6784. Min Act: -0.0001

Data Index: 896590 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.5659. Min Act: -0.0001

Data Index: 753248 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.5415. Min Act: -0.0001

Data Index: 791380 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.2323. Min Act: -0.0001

Data Index: 973736 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.5449. Min Act: -0.0001

Data Index: 1279065 (C4 (Web Text))

Max Activating Token Index: 22