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

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

Neuron 93 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1042. Min Act: -0.0000

Data Index: 687161 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0965. Min Act: -0.0000

Data Index: 123947 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0864. Min Act: -0.0000

Data Index: 135569 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1252385 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1117753 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0859. Min Act: -0.0000

Data Index: 466930 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0913. Min Act: -0.0000

Data Index: 381127 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1127171 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0849. Min Act: -0.0000

Data Index: 673732 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1296079 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0841. Min Act: -0.0000

Data Index: 740394 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1344174 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0865. Min Act: -0.0000

Data Index: 989203 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0896. Min Act: -0.0000

Data Index: 792444 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0849. Min Act: -0.0000

Data Index: 936342 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0827. Min Act: -0.0000

Data Index: 548192 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0826. Min Act: -0.0000

Data Index: 131738 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0853. Min Act: -0.0000

Data Index: 527389 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0824. Min Act: -0.0000

Data Index: 232242 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0772. Min Act: -0.0000

Data Index: 587790 (C4 (Web Text))

Max Activating Token Index: 642