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

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

Neuron 5566 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0861. Min Range: -1.0861

Max Act: 1.0861. Min Act: -0.0000

Data Index: 1049325 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9628. Min Act: -0.0000

Data Index: 950695 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9539. Min Act: -0.0000

Data Index: 806115 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8619. Min Act: -0.0000

Data Index: 77819 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1283536 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1128945 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8952. Min Act: -0.0000

Data Index: 449662 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8662. Min Act: -0.0000

Data Index: 813357 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8768. Min Act: -0.0000

Data Index: 358397 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8740. Min Act: -0.0000

Data Index: 46266 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8743. Min Act: -0.0000

Data Index: 110062 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1335276 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8673. Min Act: -0.0000

Data Index: 700612 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8470. Min Act: -0.0000

Data Index: 132940 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1336754 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8093. Min Act: -0.0000

Data Index: 344437 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8791. Min Act: -0.0000

Data Index: 94691 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.8129. Min Act: -0.0000

Data Index: 445141 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7885. Min Act: -0.0000

Data Index: 800284 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 1.0861. Min Range: -1.0861

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1138842 (C4 (Web Text))

Max Activating Token Index: 70