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

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

Neuron 1803 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: 0.0913. Min Range: -0.0913

Max Act: 0.0880. Min Act: -0.0005

Data Index: 985971 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0904. Min Act: -0.0005

Data Index: 796366 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0884. Min Act: -0.0005

Data Index: 1356371 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0005

Data Index: 284490 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0877. Min Act: -0.0005

Data Index: 200325 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0872. Min Act: -0.0004

Data Index: 327927 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0874. Min Act: -0.0005

Data Index: 1358098 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0862. Min Act: -0.0005

Data Index: 891311 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0862. Min Act: -0.0005

Data Index: 541436 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0838. Min Act: -0.0005

Data Index: 721124 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0837. Min Act: -0.0005

Data Index: 831202 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0833. Min Act: -0.0005

Data Index: 693167 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0823. Min Act: -0.0005

Data Index: 49742 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0825. Min Act: -0.0005

Data Index: 706402 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0817. Min Act: -0.0005

Data Index: 471874 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0810. Min Act: -0.0004

Data Index: 983721 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0801. Min Act: -0.0005

Data Index: 864202 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0805. Min Act: -0.0005

Data Index: 1268443 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0781. Min Act: -0.0005

Data Index: 245097 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0794. Min Act: -0.0005

Data Index: 360726 (C4 (Web Text))

Max Activating Token Index: 206