Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3064 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1175541 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1036980 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0800. Min Act: -0.0002

Data Index: 454273 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0669. Min Act: -0.0002

Data Index: 454193 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1025651 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0696. Min Act: -0.0002

Data Index: 261931 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0633. Min Act: -0.0002

Data Index: 736016 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0533. Min Act: -0.0002

Data Index: 569258 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0603. Min Act: -0.0002

Data Index: 854291 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0595. Min Act: -0.0002

Data Index: 398033 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0591. Min Act: -0.0002

Data Index: 301352 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1091545 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0544. Min Act: -0.0002

Data Index: 661484 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0535. Min Act: -0.0002

Data Index: 961421 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0610. Min Act: -0.0002

Data Index: 991755 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0571. Min Act: -0.0002

Data Index: 762393 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0565. Min Act: -0.0002

Data Index: 901506 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0588. Min Act: -0.0002

Data Index: 412397 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1043933 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0538. Min Act: -0.0002

Data Index: 770773 (C4 (Web Text))

Max Activating Token Index: 821