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

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

Neuron 3858 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: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0001

Data Index: 11875 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0649. Min Act: -0.0000

Data Index: 578973 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0591. Min Act: -0.0000

Data Index: 708756 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0578. Min Act: -0.0001

Data Index: 121083 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1017013 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0583. Min Act: -0.0000

Data Index: 919204 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1338499 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0544. Min Act: -0.0001

Data Index: 602955 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1138884 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0491. Min Act: -0.0000

Data Index: 910396 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0468. Min Act: -0.0001

Data Index: 843046 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0471. Min Act: -0.0001

Data Index: 406216 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0452. Min Act: -0.0001

Data Index: 341377 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0472. Min Act: -0.0001

Data Index: 164627 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1057353 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0400. Min Act: -0.0001

Data Index: 444028 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1168411 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0398. Min Act: -0.0001

Data Index: 285938 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1354267 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0440. Min Act: -0.0000

Data Index: 4992 (C4 (Web Text))

Max Activating Token Index: 335