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

Dataset: The Pile

Neuron 2276 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.9376. Min Act: -0.0000

Data Index: 65859 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.9741. Min Act: -0.0000

Data Index: 1199513 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8910. Min Act: -0.0000

Data Index: 216372 (The Pile)

Max Activating Token Index: 595

Text #3

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.9479. Min Act: -0.0000

Data Index: 678298 (The Pile)

Max Activating Token Index: 411

Text #4

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8881. Min Act: -0.0000

Data Index: 615553 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8328. Min Act: -0.0000

Data Index: 103588 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7460. Min Act: -0.0000

Data Index: 781166 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1666244 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7296. Min Act: -0.0000

Data Index: 387471 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1068056 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1348421 (The Pile)

Max Activating Token Index: 683

Text #11

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1315792 (The Pile)

Max Activating Token Index: 977

Text #12

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1082281 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1664498 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1835436 (The Pile)

Max Activating Token Index: 643

Text #15

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1345767 (The Pile)

Max Activating Token Index: 254

Text #16

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6957. Min Act: -0.0000

Data Index: 986452 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1927982 (The Pile)

Max Activating Token Index: 500

Text #18

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6577. Min Act: -0.0000

Data Index: 414018 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6855. Min Act: -0.0000

Data Index: 315049 (The Pile)

Max Activating Token Index: 921