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

Dataset: The Pile

Neuron 3269 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: 0.1556. Min Range: -0.1556

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1112503 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1199. Min Act: -0.0000

Data Index: 60145 (The Pile)

Max Activating Token Index: 306

Text #2

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1440282 (The Pile)

Max Activating Token Index: 965

Text #3

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1190. Min Act: -0.0000

Data Index: 266119 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1798240 (The Pile)

Max Activating Token Index: 408

Text #5

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1343030 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1147. Min Act: -0.0000

Data Index: 717322 (The Pile)

Max Activating Token Index: 360

Text #7

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1105. Min Act: -0.0000

Data Index: 745428 (The Pile)

Max Activating Token Index: 439

Text #8

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1360922 (The Pile)

Max Activating Token Index: 238

Text #9

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.0999. Min Act: -0.0000

Data Index: 292778 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1246932 (The Pile)

Max Activating Token Index: 286

Text #11

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1022. Min Act: -0.0000

Data Index: 592898 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1558830 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.0979. Min Act: -0.0000

Data Index: 731063 (The Pile)

Max Activating Token Index: 589

Text #14

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1492066 (The Pile)

Max Activating Token Index: 710

Text #15

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.0951. Min Act: -0.0000

Data Index: 830212 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1757950 (The Pile)

Max Activating Token Index: 250

Text #17

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1045452 (The Pile)

Max Activating Token Index: 978

Text #18

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.0953. Min Act: -0.0000

Data Index: 528426 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1472977 (The Pile)

Max Activating Token Index: 942