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

Dataset: The Pile

Neuron 4195 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3510. Min Act: -0.0000

Data Index: 154992 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3572. Min Act: -0.0000

Data Index: 69970 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1776242 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1360067 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1529215 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2882. Min Act: -0.0000

Data Index: 15545 (The Pile)

Max Activating Token Index: 667

Text #6

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2950. Min Act: -0.0000

Data Index: 988362 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2771. Min Act: -0.0000

Data Index: 132495 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2968. Min Act: -0.0000

Data Index: 936091 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1564519 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1133744 (The Pile)

Max Activating Token Index: 317

Text #11

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1475698 (The Pile)

Max Activating Token Index: 963

Text #12

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2650. Min Act: -0.0000

Data Index: 334507 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2813. Min Act: -0.0000

Data Index: 148650 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1361676 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2786. Min Act: -0.0000

Data Index: 643229 (The Pile)

Max Activating Token Index: 85

Text #16

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1541072 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1566761 (The Pile)

Max Activating Token Index: 68

Text #18

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1496036 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1687198 (The Pile)

Max Activating Token Index: 874