Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2316 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6727. Min Act: -0.0000

Data Index: 54746 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5899. Min Act: -0.0000

Data Index: 932150 (The Pile)

Max Activating Token Index: 118

Text #2

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5902. Min Act: 0.0000

Data Index: 649477 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5434. Min Act: -0.0000

Data Index: 697086 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5476. Min Act: -0.0000

Data Index: 572291 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1998947 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1329584 (The Pile)

Max Activating Token Index: 372

Text #7

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1683343 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5652. Min Act: -0.0000

Data Index: 349395 (The Pile)

Max Activating Token Index: 183

Text #9

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5531. Min Act: -0.0000

Data Index: 101558 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1487181 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1830694 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5000. Min Act: -0.0000

Data Index: 705051 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5341. Min Act: -0.0000

Data Index: 52789 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5046. Min Act: -0.0000

Data Index: 704483 (The Pile)

Max Activating Token Index: 507

Text #15

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1805039 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5344. Min Act: -0.0000

Data Index: 185378 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1775221 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1892422 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1438682 (The Pile)

Max Activating Token Index: 743