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

Dataset: The Pile

Neuron 1137 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6831. Min Range: -5.6831

Max Act: 5.6831. Min Act: -0.0000

Data Index: 1507267 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.6735. Min Act: -0.0000

Data Index: 1922383 (The Pile)

Max Activating Token Index: 833

Text #2

Max Range: 5.6831. Min Range: -5.6831

Max Act: 3.9148. Min Act: -0.0000

Data Index: 129625 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.3944. Min Act: -0.0000

Data Index: 1668881 (The Pile)

Max Activating Token Index: 190

Text #4

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.3555. Min Act: -0.0000

Data Index: 752324 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.3084. Min Act: -0.0000

Data Index: 360142 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.1154. Min Act: -0.0000

Data Index: 1839520 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.0832. Min Act: -0.0000

Data Index: 1297420 (The Pile)

Max Activating Token Index: 905

Text #8

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.2659. Min Act: -0.0000

Data Index: 680975 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.2553. Min Act: -0.0000

Data Index: 1144568 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.3900. Min Act: -0.0000

Data Index: 1735130 (The Pile)

Max Activating Token Index: 807

Text #11

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.3077. Min Act: -0.0000

Data Index: 1334654 (The Pile)

Max Activating Token Index: 955

Text #12

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.1787. Min Act: -0.0000

Data Index: 539327 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.1605. Min Act: -0.0000

Data Index: 589254 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.1257. Min Act: -0.0000

Data Index: 98521 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.1174. Min Act: -0.0000

Data Index: 509932 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.0848. Min Act: -0.0000

Data Index: 1879358 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 5.6831. Min Range: -5.6831

Max Act: 3.5966. Min Act: -0.0000

Data Index: 1363198 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 5.6831. Min Range: -5.6831

Max Act: 4.0239. Min Act: -0.0000

Data Index: 1024419 (The Pile)

Max Activating Token Index: 505

Text #19

Max Range: 5.6831. Min Range: -5.6831

Max Act: 3.9914. Min Act: -0.0000

Data Index: 403743 (The Pile)

Max Activating Token Index: 1008