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

Dataset: The Pile

Neuron 10 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: 1.1561. Min Range: -1.1561

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1328147 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 1.1561. Min Range: -1.1561

Max Act: 1.1184. Min Act: -0.0000

Data Index: 809235 (The Pile)

Max Activating Token Index: 698

Text #2

Max Range: 1.1561. Min Range: -1.1561

Max Act: 1.0360. Min Act: -0.0000

Data Index: 112926 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1402842 (The Pile)

Max Activating Token Index: 305

Text #4

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1572547 (The Pile)

Max Activating Token Index: 245

Text #5

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.9536. Min Act: -0.0000

Data Index: 736503 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1286292 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1383403 (The Pile)

Max Activating Token Index: 293

Text #8

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.9307. Min Act: -0.0000

Data Index: 383614 (The Pile)

Max Activating Token Index: 237

Text #9

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.8980. Min Act: -0.0000

Data Index: 960895 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1633719 (The Pile)

Max Activating Token Index: 343

Text #11

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1826771 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1266185 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1115145 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.7954. Min Act: -0.0000

Data Index: 641562 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.8759. Min Act: -0.0000

Data Index: 812268 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.8171. Min Act: -0.0000

Data Index: 655686 (The Pile)

Max Activating Token Index: 625

Text #17

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.9222. Min Act: -0.0000

Data Index: 406467 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.8101. Min Act: -0.0000

Data Index: 92924 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 1.1561. Min Range: -1.1561

Max Act: 0.8186. Min Act: -0.0000

Data Index: 472472 (The Pile)

Max Activating Token Index: 23