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

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

Neuron 171 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.8525. Min Act: -0.0000

Data Index: 962458 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.4448. Min Act: -0.0000

Data Index: 745931 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.5764. Min Act: -0.0000

Data Index: 1211823 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.2785. Min Act: -0.0000

Data Index: 1313501 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.2262. Min Act: -0.0000

Data Index: 783247 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.3560. Min Act: -0.0000

Data Index: 552891 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.2453. Min Act: -0.0000

Data Index: 546942 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.2560. Min Act: -0.0000

Data Index: 235190 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.1393. Min Act: -0.0000

Data Index: 680992 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.2499. Min Act: -0.0000

Data Index: 583791 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.2720. Min Act: -0.0000

Data Index: 143190 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.1265. Min Act: -0.0000

Data Index: 802387 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.1624. Min Act: -0.0000

Data Index: 491523 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.3464. Min Act: -0.0000

Data Index: 844431 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.1630. Min Act: -0.0000

Data Index: 691253 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1645584 (Python Code)

Max Activating Token Index: 326

Text #16

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.1062. Min Act: -0.0000

Data Index: 778021 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.2344. Min Act: -0.0000

Data Index: 1350326 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.0989. Min Act: -0.0000

Data Index: 820 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.8525. Min Range: -1.8525

Max Act: 1.0948. Min Act: -0.0000

Data Index: 1310631 (C4 (Web Text))

Max Activating Token Index: 544