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

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

Neuron 2992 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: 1.1025. Min Range: -1.1025

Max Act: 1.1025. Min Act: -0.0000

Data Index: 139112 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.9240. Min Act: -0.0000

Data Index: 124022 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1024608 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1187333 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8160. Min Act: -0.0000

Data Index: 759245 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7926. Min Act: -0.0000

Data Index: 789106 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7496. Min Act: -0.0000

Data Index: 807796 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7575. Min Act: -0.0000

Data Index: 546724 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7260. Min Act: -0.0000

Data Index: 30361 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7507. Min Act: -0.0000

Data Index: 395018 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7416. Min Act: -0.0000

Data Index: 137940 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6787. Min Act: -0.0000

Data Index: 355033 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6744. Min Act: -0.0000

Data Index: 29651 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6866. Min Act: -0.0000

Data Index: 487532 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6419. Min Act: -0.0000

Data Index: 837367 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6423. Min Act: -0.0000

Data Index: 765926 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6992. Min Act: -0.0000

Data Index: 701499 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6361. Min Act: -0.0000

Data Index: 41383 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6663. Min Act: -0.0000

Data Index: 38217 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6226. Min Act: -0.0000

Data Index: 62761 (C4 (Web Text))

Max Activating Token Index: 762