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

Dataset: The Pile

Neuron 118 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: 0.6683. Min Range: -0.6683

Max Act: 0.6039. Min Act: -0.0000

Data Index: 853298 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1191840 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.6000. Min Act: -0.0000

Data Index: 198519 (The Pile)

Max Activating Token Index: 691

Text #3

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.6683. Min Act: -0.0000

Data Index: 372655 (The Pile)

Max Activating Token Index: 325

Text #4

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1416574 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5657. Min Act: -0.0000

Data Index: 658488 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1825730 (The Pile)

Max Activating Token Index: 891

Text #7

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5091. Min Act: -0.0000

Data Index: 115253 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5465. Min Act: -0.0000

Data Index: 878704 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5169. Min Act: -0.0000

Data Index: 264174 (The Pile)

Max Activating Token Index: 824

Text #10

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5264. Min Act: -0.0000

Data Index: 662728 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4695. Min Act: -0.0000

Data Index: 942735 (The Pile)

Max Activating Token Index: 338

Text #12

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5317. Min Act: -0.0000

Data Index: 630430 (The Pile)

Max Activating Token Index: 54

Text #13

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1903607 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5231. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5144. Min Act: -0.0000

Data Index: 335507 (The Pile)

Max Activating Token Index: 347

Text #16

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1909916 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4167. Min Act: -0.0000

Data Index: 1038625 (The Pile)

Max Activating Token Index: 800

Text #18

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4792. Min Act: -0.0000

Data Index: 540362 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5004. Min Act: -0.0000

Data Index: 518274 (The Pile)

Max Activating Token Index: 323