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

Dataset: The Pile

Neuron 506 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: 1.0404. Min Range: -1.0404

Max Act: 1.0404. Min Act: -0.0000

Data Index: 1308710 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 1.0404. Min Range: -1.0404

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1898638 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.9125. Min Act: -0.0000

Data Index: 285887 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1392733 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1878475 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1698246 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8495. Min Act: -0.0000

Data Index: 72477 (The Pile)

Max Activating Token Index: 383

Text #7

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7897. Min Act: -0.0000

Data Index: 774978 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1036789 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7875. Min Act: -0.0000

Data Index: 808223 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1001331 (The Pile)

Max Activating Token Index: 124

Text #11

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7792. Min Act: -0.0000

Data Index: 443522 (The Pile)

Max Activating Token Index: 636

Text #12

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7556. Min Act: -0.0000

Data Index: 943813 (The Pile)

Max Activating Token Index: 493

Text #13

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1470024 (The Pile)

Max Activating Token Index: 502

Text #14

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7456. Min Act: -0.0000

Data Index: 132065 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7611. Min Act: -0.0000

Data Index: 1440992 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7357. Min Act: -0.0000

Data Index: 990635 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.6977. Min Act: -0.0000

Data Index: 1094579 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1448870 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1152321 (The Pile)

Max Activating Token Index: 618