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

Dataset: The Pile

Neuron 3577 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: 0.1433. Min Range: -0.1433

Max Act: 0.1309. Min Act: -0.0000

Data Index: 713299 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1274991 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1084010 (The Pile)

Max Activating Token Index: 541

Text #3

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1254. Min Act: -0.0000

Data Index: 269851 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1055176 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1315. Min Act: -0.0000

Data Index: 593259 (The Pile)

Max Activating Token Index: 741

Text #6

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1048864 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1895301 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1166. Min Act: -0.0000

Data Index: 52848 (The Pile)

Max Activating Token Index: 147

Text #9

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1119. Min Act: -0.0000

Data Index: 329471 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1283468 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1575488 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1484234 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1234. Min Act: -0.0000

Data Index: 884959 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1131. Min Act: -0.0000

Data Index: 709118 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1185. Min Act: -0.0000

Data Index: 696759 (The Pile)

Max Activating Token Index: 487

Text #16

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1183. Min Act: -0.0000

Data Index: 311623 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1217. Min Act: -0.0000

Data Index: 401470 (The Pile)

Max Activating Token Index: 894

Text #18

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1194850 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1125818 (The Pile)

Max Activating Token Index: 857