Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3863 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0903. Min Act: -0.0002

Data Index: 583192 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1004428 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0670. Min Act: -0.0002

Data Index: 297618 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0673. Min Act: -0.0002

Data Index: 26954 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0638. Min Act: -0.0001

Data Index: 680877 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0653. Min Act: -0.0002

Data Index: 300578 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0573. Min Act: -0.0001

Data Index: 215451 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0555. Min Act: -0.0001

Data Index: 863557 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0599. Min Act: -0.0001

Data Index: 148093 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0585. Min Act: -0.0001

Data Index: 800924 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0563. Min Act: -0.0001

Data Index: 480649 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0589. Min Act: -0.0001

Data Index: 76013 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0598. Min Act: -0.0002

Data Index: 371487 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0540. Min Act: -0.0001

Data Index: 495084 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1146031 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0450. Min Act: -0.0002

Data Index: 460402 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1083463 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0515. Min Act: -0.0001

Data Index: 592343 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0508. Min Act: -0.0002

Data Index: 281902 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0491. Min Act: -0.0001

Data Index: 221907 (C4 (Web Text))

Max Activating Token Index: 984