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

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

Neuron 3439 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0716. Min Act: -0.0002

Data Index: 706310 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0718. Min Act: -0.0002

Data Index: 540986 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0673. Min Act: -0.0002

Data Index: 604807 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0596. Min Act: -0.0002

Data Index: 318991 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0608. Min Act: -0.0002

Data Index: 835036 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0582. Min Act: -0.0002

Data Index: 234753 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0589. Min Act: -0.0002

Data Index: 427869 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1265608 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0562. Min Act: -0.0002

Data Index: 514495 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1264344 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1162868 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1286479 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0567. Min Act: -0.0002

Data Index: 883185 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0563. Min Act: -0.0002

Data Index: 258692 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1351077 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0582. Min Act: -0.0002

Data Index: 853556 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0535. Min Act: -0.0002

Data Index: 618153 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0563. Min Act: -0.0002

Data Index: 988239 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0552. Min Act: -0.0002

Data Index: 581193 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0530. Min Act: -0.0002

Data Index: 737307 (C4 (Web Text))

Max Activating Token Index: 404