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

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

Neuron 2393 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7806. Min Act: -0.0000

Data Index: 756540 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.8773. Min Act: -0.0000

Data Index: 298434 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1213185 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.4629. Min Act: -0.0000

Data Index: 344616 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.4796. Min Act: -0.0000

Data Index: 97715 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.3740. Min Act: -0.0000

Data Index: 373978 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.4321. Min Act: -0.0000

Data Index: 344365 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.4298. Min Act: -0.0000

Data Index: 7455 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.4060. Min Act: -0.0000

Data Index: 653955 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.3998. Min Act: -0.0000

Data Index: 660053 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.3814. Min Act: -0.0000

Data Index: 54322 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.3883. Min Act: -0.0000

Data Index: 215298 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.3652. Min Act: -0.0000

Data Index: 108634 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.1931. Min Act: -0.0000

Data Index: 963233 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.3280. Min Act: -0.0000

Data Index: 1135055 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.3748. Min Act: -0.0000

Data Index: 238737 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.2979. Min Act: -0.0000

Data Index: 1010698 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.2782. Min Act: -0.0000

Data Index: 931914 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.1695. Min Act: -0.0000

Data Index: 887204 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.1639. Min Act: 0.0000

Data Index: 1188217 (C4 (Web Text))

Max Activating Token Index: 187