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

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

Neuron 2311 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: -0.0001

Data Index: 570223 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1154524 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1622141 (Python Code)

Max Activating Token Index: 124

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1484445 (Python Code)

Max Activating Token Index: 750

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1100071 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0579. Min Act: -0.0001

Data Index: 291663 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1268303 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0659. Min Act: -0.0001

Data Index: 503843 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1583931 (Python Code)

Max Activating Token Index: 318

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0549. Min Act: -0.0001

Data Index: 511073 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0513. Min Act: -0.0001

Data Index: 873868 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0566. Min Act: -0.0001

Data Index: 419112 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1646762 (Python Code)

Max Activating Token Index: 551

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0528. Min Act: -0.0001

Data Index: 102232 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0524. Min Act: -0.0001

Data Index: 370956 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0585. Min Act: -0.0001

Data Index: 628986 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0513. Min Act: -0.0001

Data Index: 823764 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0497. Min Act: -0.0001

Data Index: 727333 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0494. Min Act: -0.0001

Data Index: 916639 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0497. Min Act: -0.0001

Data Index: 657919 (C4 (Web Text))

Max Activating Token Index: 266