Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 631 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1291. Min Act: -0.0005

Data Index: 621035 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1094. Min Act: -0.0005

Data Index: 464413 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0997. Min Act: -0.0005

Data Index: 199474 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0954. Min Act: -0.0005

Data Index: 38229 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0950. Min Act: -0.0005

Data Index: 999416 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1003. Min Act: -0.0005

Data Index: 985661 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1049. Min Act: -0.0005

Data Index: 807618 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0876. Min Act: -0.0005

Data Index: 323112 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0963. Min Act: -0.0005

Data Index: 469005 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0978. Min Act: -0.0005

Data Index: 142980 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0928. Min Act: -0.0005

Data Index: 304341 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0885. Min Act: -0.0005

Data Index: 1112323 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0902. Min Act: -0.0005

Data Index: 813337 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0890. Min Act: -0.0005

Data Index: 542160 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0888. Min Act: -0.0005

Data Index: 1035105 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0883. Min Act: -0.0005

Data Index: 1145058 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0882. Min Act: -0.0005

Data Index: 835781 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0894. Min Act: -0.0005

Data Index: 510777 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0849. Min Act: -0.0005

Data Index: 420984 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0899. Min Act: -0.0005

Data Index: 918695 (C4 (Web Text))

Max Activating Token Index: 800