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

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

Neuron 437 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0727. Min Act: -0.0002

Data Index: 309289 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1204296 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0625. Min Act: -0.0001

Data Index: 213233 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0587. Min Act: -0.0002

Data Index: 172848 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0585. Min Act: -0.0002

Data Index: 567164 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0560. Min Act: -0.0002

Data Index: 752434 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0528. Min Act: -0.0002

Data Index: 405876 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0569. Min Act: -0.0001

Data Index: 116525 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0531. Min Act: -0.0002

Data Index: 794773 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1127366 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0562. Min Act: -0.0002

Data Index: 415125 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0548. Min Act: -0.0002

Data Index: 392967 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1138240 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0511. Min Act: -0.0002

Data Index: 608899 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0524. Min Act: -0.0002

Data Index: 873048 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1226110 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1141233 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0503. Min Act: -0.0002

Data Index: 519996 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1004878 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0512. Min Act: -0.0002

Data Index: 309730 (C4 (Web Text))

Max Activating Token Index: 725