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

Dataset: The Pile

Neuron 4468 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.5549. Min Act: -0.0000

Data Index: 489535 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.5713. Min Act: -0.0000

Data Index: 61641 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1628822 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1420987 (The Pile)

Max Activating Token Index: 605

Text #4

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4969. Min Act: -0.0000

Data Index: 47276 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1982797 (The Pile)

Max Activating Token Index: 20

Text #6

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.5090. Min Act: -0.0000

Data Index: 414216 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1848382 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1887627 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1189129 (The Pile)

Max Activating Token Index: 324

Text #10

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4685. Min Act: -0.0000

Data Index: 1022169 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4602. Min Act: -0.0000

Data Index: 112278 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4774. Min Act: -0.0000

Data Index: 625208 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1950788 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1923257 (The Pile)

Max Activating Token Index: 736

Text #15

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4218. Min Act: -0.0000

Data Index: 163584 (The Pile)

Max Activating Token Index: 899

Text #16

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4414. Min Act: -0.0000

Data Index: 824983 (The Pile)

Max Activating Token Index: 800

Text #17

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1235214 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1410319 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 0.5713. Min Range: -0.5713

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1239755 (The Pile)

Max Activating Token Index: 455