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

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

Neuron 504 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1164700 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1410. Min Act: -0.0000

Data Index: 396638 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1181032 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1305. Min Act: -0.0000

Data Index: 206485 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1092440 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1231. Min Act: -0.0000

Data Index: 779735 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1249. Min Act: -0.0000

Data Index: 32147 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1173. Min Act: -0.0000

Data Index: 919296 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1207. Min Act: -0.0000

Data Index: 354120 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1228. Min Act: -0.0000

Data Index: 511612 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1265640 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1062. Min Act: -0.0000

Data Index: 927768 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1249. Min Act: -0.0000

Data Index: 998307 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1251. Min Act: -0.0000

Data Index: 437211 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1102. Min Act: -0.0000

Data Index: 960790 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1201. Min Act: -0.0000

Data Index: 21512 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1118. Min Act: -0.0000

Data Index: 753431 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1115. Min Act: -0.0000

Data Index: 138504 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1092. Min Act: -0.0000

Data Index: 133436 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1147. Min Act: -0.0000

Data Index: 673839 (C4 (Web Text))

Max Activating Token Index: 235