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

Dataset: The Pile

Neuron 3640 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: 1.8745. Min Range: -1.8745

Max Act: 1.8745. Min Act: -0.0000

Data Index: 1644996 (The Pile)

Max Activating Token Index: 938

Text #1

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.2310. Min Act: -0.0000

Data Index: 1609216 (The Pile)

Max Activating Token Index: 656

Text #2

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.1424. Min Act: -0.0000

Data Index: 1808543 (The Pile)

Max Activating Token Index: 274

Text #3

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.2117. Min Act: -0.0000

Data Index: 1176151 (The Pile)

Max Activating Token Index: 902

Text #4

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1419276 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.8745. Min Range: -1.8745

Max Act: 1.0160. Min Act: -0.0000

Data Index: 848571 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.9520. Min Act: -0.0000

Data Index: 649859 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1240204 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1376026 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1335284 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.8068. Min Act: -0.0000

Data Index: 183757 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1861913 (The Pile)

Max Activating Token Index: 348

Text #12

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1009288 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1350234 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.7767. Min Act: -0.0000

Data Index: 28274 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.8360. Min Act: -0.0000

Data Index: 265776 (The Pile)

Max Activating Token Index: 457

Text #16

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1706393 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.8414. Min Act: -0.0000

Data Index: 327603 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1698999 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 1.8745. Min Range: -1.8745

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1614422 (The Pile)

Max Activating Token Index: 530