Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3421 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1163336 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1158226 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.9348. Min Act: -0.0000

Data Index: 287823 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1012455 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7839. Min Act: -0.0000

Data Index: 647432 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1299490 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1332498 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7764. Min Act: -0.0000

Data Index: 949529 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7806. Min Act: -0.0000

Data Index: 823701 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.6385. Min Act: -0.0000

Data Index: 524549 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.6408. Min Act: -0.0000

Data Index: 16329 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.6711. Min Act: -0.0000

Data Index: 450030 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.6691. Min Act: -0.0000

Data Index: 995221 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.5657. Min Act: -0.0000

Data Index: 930950 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.5224. Min Act: -0.0000

Data Index: 349327 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.5558. Min Act: -0.0000

Data Index: 660203 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1082109 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1202472 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.5848. Min Act: -0.0000

Data Index: 725688 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.6352. Min Act: -0.0000

Data Index: 981065 (C4 (Web Text))

Max Activating Token Index: 559