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

Dataset: The Pile

Neuron 4840 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: 0.6079. Min Range: -0.6079

Max Act: 0.6079. Min Act: -0.0000

Data Index: 804161 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1950201 (The Pile)

Max Activating Token Index: 661

Text #2

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1942039 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5667. Min Act: -0.0000

Data Index: 272261 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1233338 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5456. Min Act: -0.0000

Data Index: 501623 (The Pile)

Max Activating Token Index: 266

Text #6

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5266. Min Act: -0.0000

Data Index: 601923 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5287. Min Act: -0.0000

Data Index: 962625 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1138983 (The Pile)

Max Activating Token Index: 139

Text #9

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1404194 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1903244 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1324964 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1841817 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1093747 (The Pile)

Max Activating Token Index: 405

Text #14

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1180726 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1490042 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1051591 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1261792 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4433. Min Act: -0.0000

Data Index: 577247 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4691. Min Act: -0.0000

Data Index: 980512 (The Pile)

Max Activating Token Index: 69