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

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

Neuron 1978 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1019580 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1342. Min Act: -0.0000

Data Index: 410143 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1088. Min Act: -0.0000

Data Index: 648229 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1062. Min Act: -0.0000

Data Index: 321425 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1015340 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0939. Min Act: -0.0000

Data Index: 60579 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0907. Min Act: -0.0000

Data Index: 398191 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0945. Min Act: -0.0000

Data Index: 255663 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0844. Min Act: -0.0000

Data Index: 623672 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0913. Min Act: -0.0000

Data Index: 77031 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0780. Min Act: -0.0000

Data Index: 1000362 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0836. Min Act: -0.0000

Data Index: 873236 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1343604 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0748. Min Act: -0.0000

Data Index: 759864 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1265426 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0736. Min Act: -0.0000

Data Index: 611785 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1154344 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0738. Min Act: -0.0000

Data Index: 12386 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0639. Min Act: -0.0000

Data Index: 974760 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0773. Min Act: -0.0000

Data Index: 560538 (C4 (Web Text))

Max Activating Token Index: 909