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

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

Neuron 1256 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0839. Min Act: -0.0000

Data Index: 63869 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0790. Min Act: -0.0000

Data Index: 991237 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0700. Min Act: -0.0000

Data Index: 882904 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0684. Min Act: -0.0001

Data Index: 268490 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0685. Min Act: -0.0000

Data Index: 904904 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0632. Min Act: -0.0000

Data Index: 469508 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0619. Min Act: -0.0000

Data Index: 678788 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1173291 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0643. Min Act: -0.0000

Data Index: 617789 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0632. Min Act: -0.0000

Data Index: 828434 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0626. Min Act: -0.0001

Data Index: 128443 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0538. Min Act: -0.0000

Data Index: 270393 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0681. Min Act: -0.0000

Data Index: 847425 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0627. Min Act: -0.0000

Data Index: 923751 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0513. Min Act: -0.0000

Data Index: 1045118 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1186461 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0603. Min Act: -0.0000

Data Index: 1131042 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0634. Min Act: -0.0000

Data Index: 915789 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0596. Min Act: -0.0001

Data Index: 287449 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0595. Min Act: -0.0000

Data Index: 974520 (C4 (Web Text))

Max Activating Token Index: 33