Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3213 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4656. Min Act: -0.0000

Data Index: 84199 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3563. Min Act: -0.0000

Data Index: 504854 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3688. Min Act: -0.0000

Data Index: 225204 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3667. Min Act: -0.0000

Data Index: 752450 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3436. Min Act: -0.0000

Data Index: 360457 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3153. Min Act: -0.0000

Data Index: 764059 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3006. Min Act: -0.0000

Data Index: 890302 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1337091 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2995. Min Act: -0.0000

Data Index: 41247 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2909. Min Act: -0.0000

Data Index: 938394 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3085. Min Act: -0.0000

Data Index: 808765 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2978. Min Act: -0.0000

Data Index: 688761 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1065912 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2524. Min Act: -0.0000

Data Index: 883126 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2677. Min Act: -0.0000

Data Index: 274948 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1183237 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2814. Min Act: -0.0000

Data Index: 304035 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2729. Min Act: -0.0000

Data Index: 339440 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2888. Min Act: -0.0000

Data Index: 646 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2758. Min Act: -0.0000

Data Index: 737525 (C4 (Web Text))

Max Activating Token Index: 496