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

Dataset: The Pile

Neuron 1690 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.8655. Min Act: -0.0000

Data Index: 557559 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1077559 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1002858 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1691292 (The Pile)

Max Activating Token Index: 199

Text #4

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7298. Min Act: -0.0000

Data Index: 798005 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7664. Min Act: -0.0000

Data Index: 11470 (The Pile)

Max Activating Token Index: 509

Text #6

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7943. Min Act: -0.0000

Data Index: 21721 (The Pile)

Max Activating Token Index: 792

Text #7

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7945. Min Act: -0.0000

Data Index: 159756 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1696889 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1220624 (The Pile)

Max Activating Token Index: 517

Text #10

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7165. Min Act: -0.0000

Data Index: 674850 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1883764 (The Pile)

Max Activating Token Index: 338

Text #12

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1772718 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1129058 (The Pile)

Max Activating Token Index: 95

Text #14

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1024502 (The Pile)

Max Activating Token Index: 141

Text #15

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1133165 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1157791 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.6565. Min Act: -0.0000

Data Index: 135484 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1281407 (The Pile)

Max Activating Token Index: 75

Text #19

Max Range: 0.8655. Min Range: -0.8655

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1424235 (The Pile)

Max Activating Token Index: 690