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

Dataset: The Pile

Neuron 3614 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1645963 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1671776 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1368580 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3395. Min Act: -0.0000

Data Index: 375227 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1979562 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3247. Min Act: -0.0000

Data Index: 414140 (The Pile)

Max Activating Token Index: 252

Text #6

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3407. Min Act: -0.0000

Data Index: 351575 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3261. Min Act: -0.0000

Data Index: 357676 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3251. Min Act: -0.0000

Data Index: 641473 (The Pile)

Max Activating Token Index: 209

Text #9

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1189557 (The Pile)

Max Activating Token Index: 331

Text #10

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2949. Min Act: -0.0000

Data Index: 384038 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3132. Min Act: -0.0000

Data Index: 610686 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1591183 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3289. Min Act: -0.0000

Data Index: 882045 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1708182 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1068403 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1644502 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3024. Min Act: -0.0000

Data Index: 300698 (The Pile)

Max Activating Token Index: 442

Text #18

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2949. Min Act: -0.0000

Data Index: 752031 (The Pile)

Max Activating Token Index: 265

Text #19

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1961710 (The Pile)

Max Activating Token Index: 239