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

Dataset: The Pile

Neuron 1618 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.3917. Min Act: -0.0000

Data Index: 804455 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1591040 (The Pile)

Max Activating Token Index: 930

Text #2

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1847957 (The Pile)

Max Activating Token Index: 935

Text #3

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1364898 (The Pile)

Max Activating Token Index: 882

Text #4

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9427. Min Act: -0.0000

Data Index: 28593 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1098489 (The Pile)

Max Activating Token Index: 910

Text #6

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9957. Min Act: -0.0000

Data Index: 887155 (The Pile)

Max Activating Token Index: 956

Text #7

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1491299 (The Pile)

Max Activating Token Index: 72

Text #8

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1574742 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9276. Min Act: -0.0000

Data Index: 147138 (The Pile)

Max Activating Token Index: 983

Text #10

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1300716 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8933. Min Act: -0.0000

Data Index: 608005 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1524906 (The Pile)

Max Activating Token Index: 910

Text #13

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1601919 (The Pile)

Max Activating Token Index: 937

Text #14

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9243. Min Act: -0.0000

Data Index: 921065 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9974. Min Act: -0.0000

Data Index: 204048 (The Pile)

Max Activating Token Index: 652

Text #16

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1197637 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1731353 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1932533 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9106. Min Act: -0.0000

Data Index: 490895 (The Pile)

Max Activating Token Index: 799