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

Dataset: The Pile

Neuron 372 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: 1.6521. Min Range: -1.6521

Max Act: 1.6521. Min Act: -0.0000

Data Index: 1022504 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.4323. Min Act: -0.0000

Data Index: 689052 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.2879. Min Act: -0.0000

Data Index: 1471804 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1944271 (The Pile)

Max Activating Token Index: 684

Text #4

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1584486 (The Pile)

Max Activating Token Index: 486

Text #5

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.3060. Min Act: -0.0000

Data Index: 657287 (The Pile)

Max Activating Token Index: 515

Text #6

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.3157. Min Act: -0.0000

Data Index: 1344817 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1576. Min Act: -0.0000

Data Index: 1940851 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1353819 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1259. Min Act: -0.0000

Data Index: 1932749 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1099508 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1252. Min Act: -0.0000

Data Index: 818205 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1750. Min Act: -0.0000

Data Index: 793593 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1265131 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1672213 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1074404 (The Pile)

Max Activating Token Index: 466

Text #16

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1217. Min Act: -0.0000

Data Index: 275816 (The Pile)

Max Activating Token Index: 529

Text #17

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1584011 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.0195. Min Act: -0.0000

Data Index: 1540291 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.1144. Min Act: -0.0000

Data Index: 178257 (The Pile)

Max Activating Token Index: 489