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

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

Neuron 1667 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0875. Min Act: -0.0005

Data Index: 190455 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0899. Min Act: -0.0005

Data Index: 1306765 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0899. Min Act: -0.0005

Data Index: 101971 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0877. Min Act: -0.0005

Data Index: 210471 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0869. Min Act: -0.0005

Data Index: 1243566 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0888. Min Act: -0.0005

Data Index: 778794 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0884. Min Act: -0.0005

Data Index: 794251 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0880. Min Act: -0.0005

Data Index: 988895 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0849. Min Act: -0.0005

Data Index: 68701 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0806. Min Act: -0.0005

Data Index: 406753 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0837. Min Act: -0.0005

Data Index: 394418 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0863. Min Act: -0.0005

Data Index: 395171 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0817. Min Act: -0.0005

Data Index: 346189 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0831. Min Act: -0.0005

Data Index: 461918 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0837. Min Act: -0.0005

Data Index: 209988 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0819. Min Act: -0.0005

Data Index: 1098309 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0800. Min Act: -0.0005

Data Index: 299617 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0801. Min Act: -0.0005

Data Index: 948573 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0777. Min Act: -0.0005

Data Index: 575307 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0814. Min Act: -0.0005

Data Index: 18636 (C4 (Web Text))

Max Activating Token Index: 967