Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 214 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0633. Min Act: -0.0002

Data Index: 267048 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0637. Min Act: -0.0002

Data Index: 83041 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1102200 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0601. Min Act: -0.0002

Data Index: 176279 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0618. Min Act: -0.0002

Data Index: 257873 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1335977 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0588. Min Act: -0.0002

Data Index: 525515 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0590. Min Act: -0.0002

Data Index: 841762 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0576. Min Act: -0.0002

Data Index: 43001 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0595. Min Act: -0.0002

Data Index: 19862 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0590. Min Act: -0.0002

Data Index: 307787 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1323789 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0564. Min Act: -0.0002

Data Index: 94914 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0562. Min Act: -0.0002

Data Index: 770471 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0563. Min Act: -0.0002

Data Index: 47822 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1041368 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0556. Min Act: -0.0002

Data Index: 415623 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0546. Min Act: -0.0002

Data Index: 898113 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1182027 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0540. Min Act: -0.0002

Data Index: 753488 (C4 (Web Text))

Max Activating Token Index: 128