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

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

Neuron 4125 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1203607 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1023584 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0591. Min Act: -0.0002

Data Index: 580861 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0584. Min Act: -0.0002

Data Index: 907441 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0615. Min Act: -0.0002

Data Index: 488001 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0577. Min Act: -0.0002

Data Index: 550033 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1122723 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1173446 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0558. Min Act: -0.0002

Data Index: 385032 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1187684 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0573. Min Act: -0.0002

Data Index: 605597 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0544. Min Act: -0.0002

Data Index: 279583 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1262601 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1006565 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0516. Min Act: -0.0002

Data Index: 873089 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0532. Min Act: -0.0002

Data Index: 873033 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0514. Min Act: -0.0002

Data Index: 852249 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0530. Min Act: -0.0002

Data Index: 567530 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1285267 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1291011 (C4 (Web Text))

Max Activating Token Index: 1004