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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1381 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.2753. Min Act: -0.0001

Data Index: 5364 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.2307. Min Act: -0.0001

Data Index: 1059485 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.1082. Min Act: -0.0001

Data Index: 1225483 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.1042. Min Act: -0.0001

Data Index: 278313 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0115. Min Act: -0.0001

Data Index: 323492 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9808. Min Act: -0.0001

Data Index: 1246655 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.1216. Min Act: -0.0001

Data Index: 300139 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0437. Min Act: -0.0001

Data Index: 1333160 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0130. Min Act: -0.0001

Data Index: 660779 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0315. Min Act: -0.0001

Data Index: 1048969 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9355. Min Act: -0.0001

Data Index: 455206 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9598. Min Act: -0.0001

Data Index: 196111 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0194. Min Act: -0.0001

Data Index: 491887 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9488. Min Act: -0.0001

Data Index: 1193186 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9757. Min Act: -0.0001

Data Index: 385451 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9629. Min Act: -0.0001

Data Index: 1186662 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.8560. Min Act: -0.0001

Data Index: 796744 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9434. Min Act: -0.0001

Data Index: 302408 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.8791. Min Act: -0.0001

Data Index: 713080 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9214. Min Act: -0.0001

Data Index: 125521 (C4 (Web Text))

Max Activating Token Index: 17