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

Dataset: The Pile

Neuron 1509 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: 0.7943. Min Range: -0.7943

Max Act: 0.7606. Min Act: -0.0000

Data Index: 81836 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7943. Min Act: -0.0000

Data Index: 433864 (The Pile)

Max Activating Token Index: 864

Text #2

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1750606 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7132. Min Act: -0.0000

Data Index: 77733 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1559489 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1029923 (The Pile)

Max Activating Token Index: 832

Text #6

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6340. Min Act: -0.0000

Data Index: 509721 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6376. Min Act: -0.0000

Data Index: 506687 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5557. Min Act: -0.0000

Data Index: 130519 (The Pile)

Max Activating Token Index: 675

Text #9

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5925. Min Act: -0.0000

Data Index: 819108 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1118096 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1200170 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1384208 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5638. Min Act: -0.0000

Data Index: 301709 (The Pile)

Max Activating Token Index: 167

Text #14

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6068. Min Act: -0.0000

Data Index: 342071 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5437. Min Act: -0.0000

Data Index: 186300 (The Pile)

Max Activating Token Index: 328

Text #16

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1832681 (The Pile)

Max Activating Token Index: 774

Text #17

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5576. Min Act: -0.0000

Data Index: 761085 (The Pile)

Max Activating Token Index: 985

Text #18

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5415. Min Act: -0.0000

Data Index: 48512 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1145767 (The Pile)

Max Activating Token Index: 912