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

Dataset: The Pile

Neuron 5088 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1265905 (The Pile)

Max Activating Token Index: 572

Text #1

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1153772 (The Pile)

Max Activating Token Index: 665

Text #2

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.8238. Min Act: -0.0000

Data Index: 523438 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.8201. Min Act: -0.0000

Data Index: 1436643 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.8379. Min Act: -0.0000

Data Index: 618435 (The Pile)

Max Activating Token Index: 675

Text #5

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1570446 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1732186 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1835728 (The Pile)

Max Activating Token Index: 963

Text #8

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7401. Min Act: -0.0000

Data Index: 796183 (The Pile)

Max Activating Token Index: 653

Text #9

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1406286 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1130544 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1829080 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7305. Min Act: -0.0000

Data Index: 920577 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6250. Min Act: -0.0000

Data Index: 337886 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7123. Min Act: -0.0000

Data Index: 996604 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7415. Min Act: -0.0000

Data Index: 978600 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1864954 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7789. Min Act: -0.0000

Data Index: 742937 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1422139 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7256. Min Act: -0.0000

Data Index: 162300 (The Pile)

Max Activating Token Index: 594