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

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

Neuron 5019 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4372. Min Range: -5.4372

Max Act: 5.4372. Min Act: 0.0000

Data Index: 175639 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 5.4372. Min Range: -5.4372

Max Act: 4.5912. Min Act: -0.0000

Data Index: 636084 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.9429. Min Act: -0.0000

Data Index: 758596 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.9613. Min Act: -0.0000

Data Index: 300316 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.9235. Min Act: -0.0000

Data Index: 1342808 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.6615. Min Act: -0.0000

Data Index: 1336287 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.7852. Min Act: -0.0000

Data Index: 329213 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.7262. Min Act: -0.0000

Data Index: 154164 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.6133. Min Act: -0.0000

Data Index: 762432 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.2588. Min Act: -0.0000

Data Index: 523583 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.3711. Min Act: 0.0001

Data Index: 212748 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.7113. Min Act: -0.0000

Data Index: 923873 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.6273. Min Act: -0.0000

Data Index: 665544 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.5051. Min Act: -0.0000

Data Index: 671646 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.3845. Min Act: -0.0000

Data Index: 1170469 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.2801. Min Act: -0.0000

Data Index: 1295745 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 5.4372. Min Range: -5.4372

Max Act: 2.9899. Min Act: -0.0000

Data Index: 698897 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.2919. Min Act: -0.0000

Data Index: 833998 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.2526. Min Act: -0.0000

Data Index: 994316 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 5.4372. Min Range: -5.4372

Max Act: 3.2475. Min Act: -0.0000

Data Index: 369346 (C4 (Web Text))

Max Activating Token Index: 88