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

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

Neuron 2633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1252251 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0603. Min Act: -0.0001

Data Index: 648841 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0600. Min Act: -0.0001

Data Index: 827645 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1479408 (Python Code)

Max Activating Token Index: 499

Text #4

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0573. Min Act: -0.0001

Data Index: 699351 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0562. Min Act: -0.0001

Data Index: 324519 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1105314 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0528. Min Act: -0.0000

Data Index: 278364 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0582. Min Act: -0.0001

Data Index: 437285 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1301046 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0549. Min Act: -0.0000

Data Index: 634460 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0567. Min Act: -0.0001

Data Index: 249590 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0524. Min Act: -0.0001

Data Index: 945607 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1371281 (Python Code)

Max Activating Token Index: 949

Text #14

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0564. Min Act: -0.0001

Data Index: 742637 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1068868 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0511. Min Act: -0.0001

Data Index: 245209 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1590281 (Python Code)

Max Activating Token Index: 954

Text #18

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1280968 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1340170 (C4 (Web Text))

Max Activating Token Index: 695