Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1776 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.1001. Min Act: -0.0001

Data Index: 422235 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1223564 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0853. Min Act: -0.0001

Data Index: 160068 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0885. Min Act: -0.0001

Data Index: 942423 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0703. Min Act: -0.0001

Data Index: 708242 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0773. Min Act: -0.0001

Data Index: 883614 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1080092 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0764. Min Act: -0.0001

Data Index: 34620 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0816. Min Act: -0.0001

Data Index: 321672 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0868. Min Act: -0.0001

Data Index: 755387 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1255883 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0750. Min Act: -0.0001

Data Index: 281544 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0742. Min Act: -0.0001

Data Index: 197997 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0721. Min Act: -0.0001

Data Index: 953121 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0740. Min Act: -0.0001

Data Index: 709856 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0759. Min Act: -0.0001

Data Index: 921840 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0739. Min Act: -0.0001

Data Index: 336711 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0706. Min Act: -0.0001

Data Index: 667876 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1259444 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1127941 (C4 (Web Text))

Max Activating Token Index: 28