Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1047 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0994. Min Act: -0.0002

Data Index: 69909 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1004558 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0926. Min Act: -0.0002

Data Index: 848010 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0914. Min Act: -0.0002

Data Index: 164541 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0883. Min Act: -0.0002

Data Index: 313297 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0838. Min Act: -0.0002

Data Index: 182127 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1356682 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1282793 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1028664 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1100508 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0849. Min Act: -0.0002

Data Index: 300711 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0834. Min Act: -0.0002

Data Index: 835999 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1288703 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0825. Min Act: -0.0002

Data Index: 667400 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0814. Min Act: -0.0002

Data Index: 301565 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0819. Min Act: -0.0002

Data Index: 591412 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1203908 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0819. Min Act: -0.0002

Data Index: 804174 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0821. Min Act: -0.0002

Data Index: 519135 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0842. Min Act: -0.0002

Data Index: 258334 (C4 (Web Text))

Max Activating Token Index: 35