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

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

Neuron 233 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: 0.0860. Min Range: -0.0860

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1124144 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0853. Min Act: -0.0001

Data Index: 895822 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0825. Min Act: -0.0001

Data Index: 170328 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1113099 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0689. Min Act: -0.0001

Data Index: 841490 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0763. Min Act: -0.0001

Data Index: 350935 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0761. Min Act: -0.0001

Data Index: 400182 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1250700 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0734. Min Act: -0.0001

Data Index: 241096 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0755. Min Act: -0.0001

Data Index: 387978 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0761. Min Act: -0.0001

Data Index: 254586 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0707. Min Act: -0.0001

Data Index: 158363 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0697. Min Act: -0.0001

Data Index: 873176 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0731. Min Act: -0.0001

Data Index: 656825 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0726. Min Act: -0.0001

Data Index: 728863 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0690. Min Act: -0.0001

Data Index: 18102 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0708. Min Act: -0.0001

Data Index: 235027 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0672. Min Act: -0.0001

Data Index: 269186 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0687. Min Act: -0.0002

Data Index: 671458 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1052003 (C4 (Web Text))

Max Activating Token Index: 264