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

Dataset: The Pile

Neuron 235 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: 0.1120. Min Range: -0.1120

Max Act: 0.1120. Min Act: -0.0000

Data Index: 354074 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1971984 (The Pile)

Max Activating Token Index: 840

Text #2

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1003. Min Act: -0.0000

Data Index: 964041 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1335216 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0967. Min Act: -0.0000

Data Index: 714640 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1781620 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0925. Min Act: -0.0000

Data Index: 454820 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0965. Min Act: -0.0000

Data Index: 235922 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1171471 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0948. Min Act: -0.0000

Data Index: 183871 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1006. Min Act: -0.0000

Data Index: 663755 (The Pile)

Max Activating Token Index: 246

Text #11

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0939. Min Act: 0.0000

Data Index: 1849787 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1162410 (The Pile)

Max Activating Token Index: 673

Text #13

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0974. Min Act: -0.0000

Data Index: 825919 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1114920 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0936. Min Act: -0.0000

Data Index: 563810 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0924. Min Act: -0.0000

Data Index: 592681 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1100579 (The Pile)

Max Activating Token Index: 838

Text #18

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0885. Min Act: -0.0000

Data Index: 97828 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0900. Min Act: -0.0000

Data Index: 44897 (The Pile)

Max Activating Token Index: 410