Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 849 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.8101. Min Act: -0.0001

Data Index: 679885 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7076. Min Act: -0.0001

Data Index: 702744 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6493. Min Act: -0.0001

Data Index: 469374 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7373. Min Act: -0.0001

Data Index: 886544 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6718. Min Act: -0.0001

Data Index: 1116693 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6959. Min Act: -0.0001

Data Index: 869297 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6733. Min Act: -0.0001

Data Index: 758316 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6538. Min Act: -0.0001

Data Index: 513592 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6396. Min Act: -0.0001

Data Index: 1302330 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5699. Min Act: -0.0001

Data Index: 948502 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5661. Min Act: -0.0001

Data Index: 1650387 (Python Code)

Max Activating Token Index: 880

Text #11

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6250. Min Act: -0.0001

Data Index: 493869 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6232. Min Act: -0.0001

Data Index: 286960 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5940. Min Act: -0.0001

Data Index: 1620990 (Python Code)

Max Activating Token Index: 651

Text #14

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6185. Min Act: -0.0001

Data Index: 1349165 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6247. Min Act: -0.0001

Data Index: 1539445 (Python Code)

Max Activating Token Index: 837

Text #16

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6276. Min Act: -0.0001

Data Index: 1402917 (Python Code)

Max Activating Token Index: 547

Text #17

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6095. Min Act: -0.0001

Data Index: 605982 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5912. Min Act: -0.0001

Data Index: 1546316 (Python Code)

Max Activating Token Index: 551

Text #19

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5114. Min Act: -0.0001

Data Index: 323908 (C4 (Web Text))

Max Activating Token Index: 851