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

Dataset: The Pile

Neuron 2386 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: 0.8187. Min Range: -0.8187

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1979621 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.8187. Min Act: -0.0000

Data Index: 203257 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.7125. Min Act: -0.0000

Data Index: 507330 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.7237. Min Act: -0.0000

Data Index: 273715 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5902. Min Act: -0.0000

Data Index: 147204 (The Pile)

Max Activating Token Index: 388

Text #5

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6123. Min Act: -0.0000

Data Index: 374167 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1585097 (The Pile)

Max Activating Token Index: 740

Text #7

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5850. Min Act: -0.0000

Data Index: 874097 (The Pile)

Max Activating Token Index: 310

Text #8

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6469. Min Act: -0.0000

Data Index: 549068 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1464731 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1653284 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5489. Min Act: -0.0000

Data Index: 968377 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6425. Min Act: -0.0000

Data Index: 522441 (The Pile)

Max Activating Token Index: 904

Text #13

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1095344 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1649823 (The Pile)

Max Activating Token Index: 778

Text #15

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1643371 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5748. Min Act: -0.0000

Data Index: 432291 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1118279 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1485083 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5348. Min Act: -0.0000

Data Index: 54512 (The Pile)

Max Activating Token Index: 359