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

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

Neuron 1392 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: 0.1008. Min Range: -0.1008

Max Act: 0.1008. Min Act: -0.0001

Data Index: 887976 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0938. Min Act: -0.0002

Data Index: 372435 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0909. Min Act: -0.0002

Data Index: 579702 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1267757 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0996. Min Act: -0.0002

Data Index: 233234 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0879. Min Act: -0.0002

Data Index: 265078 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0871. Min Act: -0.0002

Data Index: 141054 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0861. Min Act: -0.0002

Data Index: 423615 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0817. Min Act: -0.0002

Data Index: 625630 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1142476 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0759. Min Act: -0.0002

Data Index: 9407 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0801. Min Act: -0.0002

Data Index: 507408 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0760. Min Act: -0.0002

Data Index: 785213 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1302997 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0760. Min Act: -0.0002

Data Index: 301247 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0735. Min Act: -0.0002

Data Index: 483562 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1178492 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1174148 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0785. Min Act: -0.0001

Data Index: 837728 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0760. Min Act: -0.0002

Data Index: 231891 (C4 (Web Text))

Max Activating Token Index: 183