Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3501 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0674. Min Range: -1.0674

Max Act: 1.0674. Min Act: -0.0000

Data Index: 4327 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1330611 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.7807. Min Act: -0.0000

Data Index: 460915 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1572291 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1518940 (Python Code)

Max Activating Token Index: 511

Text #5

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.8318. Min Act: -0.0000

Data Index: 29877 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1649218 (Python Code)

Max Activating Token Index: 375

Text #7

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1406960 (Python Code)

Max Activating Token Index: 431

Text #8

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.7831. Min Act: -0.0000

Data Index: 62618 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1100899 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.7470. Min Act: -0.0000

Data Index: 899076 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.7261. Min Act: -0.0000

Data Index: 462992 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.7772. Min Act: -0.0000

Data Index: 289914 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1566315 (Python Code)

Max Activating Token Index: 132

Text #14

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.7917. Min Act: -0.0000

Data Index: 196468 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.5567. Min Act: -0.0000

Data Index: 885191 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.5563. Min Act: -0.0000

Data Index: 535928 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1581836 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1441052 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 1.0674. Min Range: -1.0674

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1037730 (C4 (Web Text))

Max Activating Token Index: 275