Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4094 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1508796 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1166. Min Act: -0.0000

Data Index: 517934 (The Pile)

Max Activating Token Index: 474

Text #2

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1239. Min Act: -0.0000

Data Index: 477599 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1160. Min Act: -0.0000

Data Index: 973942 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1138. Min Act: -0.0000

Data Index: 85083 (The Pile)

Max Activating Token Index: 643

Text #5

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1198. Min Act: -0.0000

Data Index: 508408 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1632433 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1126604 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1856558 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1122. Min Act: -0.0000

Data Index: 170539 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1268424 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1278477 (The Pile)

Max Activating Token Index: 875

Text #12

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1123. Min Act: -0.0000

Data Index: 112844 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0938. Min Act: -0.0000

Data Index: 594733 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1902751 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0950. Min Act: -0.0000

Data Index: 564335 (The Pile)

Max Activating Token Index: 286

Text #16

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1331530 (The Pile)

Max Activating Token Index: 721

Text #17

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0979. Min Act: -0.0000

Data Index: 647934 (The Pile)

Max Activating Token Index: 857

Text #18

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1576860 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1149811 (The Pile)

Max Activating Token Index: 425