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

Dataset: The Pile

Neuron 926 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1236489 (The Pile)

Max Activating Token Index: 624

Text #1

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.6024. Min Act: -0.0000

Data Index: 979135 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5120. Min Act: -0.0000

Data Index: 678059 (The Pile)

Max Activating Token Index: 822

Text #3

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5734. Min Act: -0.0000

Data Index: 26783 (The Pile)

Max Activating Token Index: 791

Text #4

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5893. Min Act: -0.0000

Data Index: 614996 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1609014 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.7092. Min Act: -0.0000

Data Index: 778796 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5747. Min Act: -0.0000

Data Index: 630796 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5159. Min Act: -0.0000

Data Index: 495310 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.6770. Min Act: -0.0000

Data Index: 998680 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5882. Min Act: -0.0000

Data Index: 271966 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5027. Min Act: -0.0000

Data Index: 286043 (The Pile)

Max Activating Token Index: 921

Text #12

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1679044 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.6546. Min Act: -0.0000

Data Index: 118061 (The Pile)

Max Activating Token Index: 950

Text #14

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1430197 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.4904. Min Act: -0.0000

Data Index: 787013 (The Pile)

Max Activating Token Index: 839

Text #16

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1365858 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1208298 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5599. Min Act: -0.0000

Data Index: 396476 (The Pile)

Max Activating Token Index: 887

Text #19

Max Range: 0.7092. Min Range: -0.7092

Max Act: 0.5580. Min Act: -0.0000

Data Index: 405508 (The Pile)

Max Activating Token Index: 790