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

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

Neuron 1203 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1085927 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0895. Min Act: -0.0001

Data Index: 137679 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0821. Min Act: -0.0001

Data Index: 428368 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0877. Min Act: -0.0000

Data Index: 740679 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0833. Min Act: -0.0001

Data Index: 105919 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0850. Min Act: -0.0001

Data Index: 997082 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0852. Min Act: -0.0001

Data Index: 263890 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1110832 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0825. Min Act: -0.0001

Data Index: 490096 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1186223 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0826. Min Act: -0.0001

Data Index: 786424 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0799. Min Act: -0.0001

Data Index: 902147 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1104314 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0789. Min Act: -0.0001

Data Index: 959157 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0786. Min Act: -0.0001

Data Index: 189183 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1254578 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0756. Min Act: -0.0001

Data Index: 53338 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0765. Min Act: -0.0001

Data Index: 7536 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0773. Min Act: -0.0000

Data Index: 864789 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0759. Min Act: -0.0001

Data Index: 632681 (C4 (Web Text))

Max Activating Token Index: 930