Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2160 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0484. Min Range: -1.0484

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1263491 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8486. Min Act: -0.0000

Data Index: 90771 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7657. Min Act: -0.0000

Data Index: 409346 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1179181 (The Pile)

Max Activating Token Index: 669

Text #4

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1256423 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1665285 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7391. Min Act: -0.0000

Data Index: 481920 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1029670 (The Pile)

Max Activating Token Index: 94

Text #8

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.6913. Min Act: 0.0000

Data Index: 204522 (The Pile)

Max Activating Token Index: 72

Text #9

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1047945 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7615. Min Act: -0.0000

Data Index: 578380 (The Pile)

Max Activating Token Index: 182

Text #11

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7355. Min Act: -0.0000

Data Index: 144904 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1202918 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1193626 (The Pile)

Max Activating Token Index: 888

Text #14

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1930508 (The Pile)

Max Activating Token Index: 250

Text #15

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1633719 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.6046. Min Act: -0.0000

Data Index: 709725 (The Pile)

Max Activating Token Index: 631

Text #17

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1746418 (The Pile)

Max Activating Token Index: 733

Text #18

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.6847. Min Act: 0.0000

Data Index: 716035 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.6329. Min Act: -0.0000

Data Index: 658386 (The Pile)

Max Activating Token Index: 57