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

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

Neuron 2007 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2519. Min Range: -1.2519

Max Act: 1.2519. Min Act: -0.0001

Data Index: 1322935 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.9427. Min Act: -0.0001

Data Index: 202796 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.9426. Min Act: -0.0001

Data Index: 141949 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.9599. Min Act: -0.0001

Data Index: 1238264 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8989. Min Act: -0.0001

Data Index: 1326680 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8983. Min Act: -0.0001

Data Index: 15001 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8808. Min Act: -0.0000

Data Index: 770493 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8914. Min Act: -0.0001

Data Index: 281652 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.9185. Min Act: -0.0000

Data Index: 369635 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8891. Min Act: -0.0001

Data Index: 587107 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8334. Min Act: -0.0001

Data Index: 857922 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.9097. Min Act: -0.0001

Data Index: 961853 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8614. Min Act: -0.0001

Data Index: 473329 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.9144. Min Act: -0.0001

Data Index: 991171 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8688. Min Act: -0.0000

Data Index: 775452 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8457. Min Act: -0.0001

Data Index: 721844 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8354. Min Act: -0.0001

Data Index: 763790 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8072. Min Act: -0.0001

Data Index: 697091 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8655. Min Act: -0.0001

Data Index: 1050712 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 1.2519. Min Range: -1.2519

Max Act: 0.8104. Min Act: -0.0001

Data Index: 628697 (C4 (Web Text))

Max Activating Token Index: 662