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

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

Neuron 1070 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.4604. Min Act: -0.0000

Data Index: 987638 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1350336 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.3109. Min Act: -0.0000

Data Index: 802414 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2999. Min Act: -0.0001

Data Index: 562428 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2966. Min Act: -0.0000

Data Index: 755084 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2887. Min Act: -0.0000

Data Index: 53473 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.3054. Min Act: 0.0000

Data Index: 533531 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.3018. Min Act: -0.0000

Data Index: 178851 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1026304 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2863. Min Act: -0.0000

Data Index: 692837 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2816. Min Act: -0.0000

Data Index: 963745 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2977. Min Act: -0.0001

Data Index: 951115 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1008956 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2699. Min Act: -0.0000

Data Index: 27666 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2594. Min Act: -0.0000

Data Index: 1303619 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2755. Min Act: -0.0000

Data Index: 985009 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2551. Min Act: -0.0000

Data Index: 727164 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1149729 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1073227 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1028026 (C4 (Web Text))

Max Activating Token Index: 519