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

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

Neuron 3051 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0716. Min Act: -0.0001

Data Index: 13724 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0713. Min Act: -0.0001

Data Index: 9277 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1020421 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0666. Min Act: -0.0001

Data Index: 373285 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0663. Min Act: -0.0001

Data Index: 230795 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0639. Min Act: -0.0001

Data Index: 833972 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1357174 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0668. Min Act: -0.0001

Data Index: 188931 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0615. Min Act: -0.0000

Data Index: 544003 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1018924 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0653. Min Act: -0.0001

Data Index: 103429 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0599. Min Act: -0.0000

Data Index: 769958 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1317722 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1320761 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0582. Min Act: -0.0001

Data Index: 988906 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0550. Min Act: -0.0001

Data Index: 275126 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0673. Min Act: -0.0001

Data Index: 118581 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0625. Min Act: -0.0001

Data Index: 374270 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0596. Min Act: -0.0001

Data Index: 506302 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1446851 (Python Code)

Max Activating Token Index: 171