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

Dataset: The Pile

Neuron 4897 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.3189. Min Act: -0.0000

Data Index: 727145 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.3085. Min Act: -0.0000

Data Index: 940831 (The Pile)

Max Activating Token Index: 262

Text #2

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2581. Min Act: -0.0000

Data Index: 624204 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1023665 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1996908 (The Pile)

Max Activating Token Index: 187

Text #5

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1848. Min Act: -0.0000

Data Index: 59245 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2209. Min Act: -0.0000

Data Index: 537174 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1092779 (The Pile)

Max Activating Token Index: 668

Text #8

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1734. Min Act: -0.0000

Data Index: 349999 (The Pile)

Max Activating Token Index: 415

Text #9

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1891. Min Act: -0.0000

Data Index: 944915 (The Pile)

Max Activating Token Index: 164

Text #10

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1723. Min Act: -0.0000

Data Index: 232445 (The Pile)

Max Activating Token Index: 507

Text #11

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1776781 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1660442 (The Pile)

Max Activating Token Index: 690

Text #13

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1713. Min Act: -0.0000

Data Index: 31431 (The Pile)

Max Activating Token Index: 303

Text #14

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1603100 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1586. Min Act: -0.0000

Data Index: 504623 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1594. Min Act: -0.0000

Data Index: 590029 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1358998 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1392187 (The Pile)

Max Activating Token Index: 925

Text #19

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1876689 (The Pile)

Max Activating Token Index: 65