Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1466 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0740. Min Act: -0.0004

Data Index: 591975 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0675. Min Act: -0.0004

Data Index: 1322632 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0661. Min Act: -0.0004

Data Index: 1016968 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0617. Min Act: -0.0004

Data Index: 1261532 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0666. Min Act: -0.0004

Data Index: 178976 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0550. Min Act: -0.0004

Data Index: 556657 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0559. Min Act: -0.0004

Data Index: 479318 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0580. Min Act: -0.0004

Data Index: 278818 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0559. Min Act: -0.0004

Data Index: 1009283 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0588. Min Act: -0.0004

Data Index: 1204329 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0487. Min Act: -0.0004

Data Index: 1160822 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0566. Min Act: -0.0004

Data Index: 862779 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0516. Min Act: -0.0004

Data Index: 665961 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0511. Min Act: -0.0004

Data Index: 135483 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0551. Min Act: -0.0004

Data Index: 874913 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0527. Min Act: -0.0004

Data Index: 538485 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0486. Min Act: -0.0004

Data Index: 1357332 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0522. Min Act: -0.0004

Data Index: 1273770 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0498. Min Act: -0.0004

Data Index: 816131 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0519. Min Act: -0.0004

Data Index: 1013127 (C4 (Web Text))

Max Activating Token Index: 394