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

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

Neuron 614 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: 0.1153. Min Range: -0.1153

Max Act: 0.1153. Min Act: -0.0000

Data Index: 282601 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1113. Min Act: -0.0000

Data Index: 580418 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1138252 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1014. Min Act: -0.0000

Data Index: 426892 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0967. Min Act: -0.0000

Data Index: 139338 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0882. Min Act: -0.0000

Data Index: 319364 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1031. Min Act: -0.0000

Data Index: 269217 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0885. Min Act: -0.0000

Data Index: 911961 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0817. Min Act: -0.0000

Data Index: 585257 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1258171 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0888. Min Act: -0.0000

Data Index: 211642 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0894. Min Act: -0.0000

Data Index: 254079 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0826. Min Act: -0.0000

Data Index: 135812 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0914. Min Act: -0.0000

Data Index: 641845 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0871. Min Act: -0.0000

Data Index: 171088 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0880. Min Act: -0.0000

Data Index: 863961 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1300024 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0885. Min Act: -0.0000

Data Index: 696448 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0873. Min Act: -0.0000

Data Index: 1572164 (Python Code)

Max Activating Token Index: 325

Text #19

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0826. Min Act: -0.0000

Data Index: 891768 (C4 (Web Text))

Max Activating Token Index: 843