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

Dataset: The Pile

Neuron 1992 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: 0.7056. Min Range: -0.7056

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1621778 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.7056. Min Act: -0.0000

Data Index: 975353 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1664666 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.6236. Min Act: -0.0000

Data Index: 568225 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.6076. Min Act: -0.0000

Data Index: 355243 (The Pile)

Max Activating Token Index: 809

Text #5

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5617. Min Act: -0.0000

Data Index: 900472 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5942. Min Act: -0.0000

Data Index: 923551 (The Pile)

Max Activating Token Index: 660

Text #7

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5599. Min Act: -0.0000

Data Index: 540720 (The Pile)

Max Activating Token Index: 877

Text #8

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1622542 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5668. Min Act: -0.0000

Data Index: 684160 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5391. Min Act: -0.0000

Data Index: 825098 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1228041 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5862. Min Act: -0.0000

Data Index: 574615 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1294006 (The Pile)

Max Activating Token Index: 903

Text #14

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5071. Min Act: -0.0000

Data Index: 712308 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1919648 (The Pile)

Max Activating Token Index: 983

Text #16

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1875013 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1160255 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5409. Min Act: -0.0000

Data Index: 26618 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1277289 (The Pile)

Max Activating Token Index: 459