Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 170 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.7867. Min Act: -0.0000

Data Index: 227388 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.7103. Min Act: -0.0000

Data Index: 631284 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.7018. Min Act: -0.0000

Data Index: 11812 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1083065 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5900. Min Act: -0.0000

Data Index: 988674 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5560. Min Act: -0.0000

Data Index: 131131 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5920. Min Act: -0.0000

Data Index: 652973 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5669. Min Act: -0.0000

Data Index: 445159 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5667. Min Act: -0.0000

Data Index: 113905 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1153472 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5563. Min Act: -0.0000

Data Index: 997040 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.6403. Min Act: -0.0000

Data Index: 306992 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5556. Min Act: -0.0000

Data Index: 482103 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5334. Min Act: -0.0000

Data Index: 347117 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1032865 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5290. Min Act: -0.0000

Data Index: 173041 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5434. Min Act: -0.0000

Data Index: 898848 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5632. Min Act: -0.0000

Data Index: 996447 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1094524 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.7867. Min Range: -0.7867

Max Act: 0.5440. Min Act: -0.0000

Data Index: 985655 (C4 (Web Text))

Max Activating Token Index: 485