Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3399 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.4014. Min Act: -0.0000

Data Index: 456065 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.8718. Min Act: -0.0000

Data Index: 30623 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1139901 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.8338. Min Act: -0.0000

Data Index: 944837 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1353503 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1140016 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.6457. Min Act: -0.0000

Data Index: 888691 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1315136 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5268. Min Act: -0.0000

Data Index: 355719 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5938. Min Act: -0.0000

Data Index: 815663 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5874. Min Act: -0.0000

Data Index: 134977 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1009405 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5939. Min Act: -0.0000

Data Index: 175629 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5185. Min Act: -0.0000

Data Index: 883457 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1222995 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5534. Min Act: -0.0000

Data Index: 192673 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5488. Min Act: -0.0000

Data Index: 708617 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5144. Min Act: -0.0000

Data Index: 217614 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5359. Min Act: -0.0000

Data Index: 751934 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.5187. Min Act: -0.0000

Data Index: 345107 (C4 (Web Text))

Max Activating Token Index: 524