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

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

Neuron 2725 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.9490. Min Act: -0.0002

Data Index: 882236 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.9284. Min Act: -0.0001

Data Index: 709153 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8158. Min Act: -0.0001

Data Index: 994576 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8470. Min Act: -0.0001

Data Index: 727497 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8476. Min Act: -0.0002

Data Index: 79334 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8689. Min Act: -0.0002

Data Index: 496344 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8102. Min Act: -0.0001

Data Index: 603810 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8208. Min Act: -0.0002

Data Index: 63800 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8420. Min Act: -0.0001

Data Index: 997860 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8090. Min Act: -0.0001

Data Index: 917101 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8093. Min Act: -0.0001

Data Index: 959780 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8067. Min Act: -0.0002

Data Index: 207539 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.7249. Min Act: -0.0002

Data Index: 723099 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.8081. Min Act: -0.0002

Data Index: 876646 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.7849. Min Act: -0.0002

Data Index: 463961 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.7551. Min Act: -0.0002

Data Index: 232770 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.7293. Min Act: -0.0001

Data Index: 1045908 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.7452. Min Act: -0.0002

Data Index: 400383 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.6732. Min Act: -0.0002

Data Index: 614157 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.9490. Min Range: -0.9490

Max Act: 0.7313. Min Act: -0.0001

Data Index: 105511 (C4 (Web Text))

Max Activating Token Index: 922