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

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

Neuron 6025 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.8850. Min Act: -0.0000

Data Index: 837102 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.7826. Min Act: -0.0000

Data Index: 174044 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.7731. Min Act: -0.0001

Data Index: 69242 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.8289. Min Act: -0.0000

Data Index: 823084 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.7278. Min Act: -0.0001

Data Index: 53147 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.6069. Min Act: -0.0000

Data Index: 632553 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.6246. Min Act: -0.0001

Data Index: 663482 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5834. Min Act: -0.0001

Data Index: 37426 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4900. Min Act: -0.0001

Data Index: 563178 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5566. Min Act: -0.0001

Data Index: 457945 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4473. Min Act: -0.0000

Data Index: 1143745 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.6133. Min Act: -0.0000

Data Index: 1246961 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5817. Min Act: -0.0000

Data Index: 1311491 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4842. Min Act: -0.0001

Data Index: 154136 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4487. Min Act: -0.0000

Data Index: 1060688 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4437. Min Act: -0.0000

Data Index: 1063535 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3959. Min Act: -0.0001

Data Index: 346279 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3870. Min Act: -0.0000

Data Index: 605733 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3705. Min Act: -0.0001

Data Index: 1353232 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3659. Min Act: -0.0001

Data Index: 800514 (C4 (Web Text))

Max Activating Token Index: 975