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

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

Neuron 2968 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0982. Min Range: -1.0982

Max Act: 1.0982. Min Act: -0.0001

Data Index: 954804 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.8050. Min Act: -0.0000

Data Index: 567087 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.8928. Min Act: -0.0000

Data Index: 795897 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.8957. Min Act: -0.0001

Data Index: 496760 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.8006. Min Act: -0.0000

Data Index: 467192 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7649. Min Act: -0.0001

Data Index: 637551 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7737. Min Act: -0.0001

Data Index: 1272307 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.8101. Min Act: -0.0001

Data Index: 552232 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7843. Min Act: -0.0000

Data Index: 76689 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7918. Min Act: -0.0001

Data Index: 347371 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7704. Min Act: -0.0001

Data Index: 315992 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7567. Min Act: -0.0001

Data Index: 1291582 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7743. Min Act: -0.0001

Data Index: 123377 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7451. Min Act: -0.0001

Data Index: 951988 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7358. Min Act: -0.0001

Data Index: 27653 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7511. Min Act: -0.0001

Data Index: 140672 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7500. Min Act: -0.0001

Data Index: 421766 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.6986. Min Act: -0.0001

Data Index: 705976 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.6955. Min Act: -0.0001

Data Index: 139589 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 1.0982. Min Range: -1.0982

Max Act: 0.7347. Min Act: -0.0001

Data Index: 637483 (C4 (Web Text))

Max Activating Token Index: 935