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

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

Neuron 3558 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1782. Min Act: -0.0000

Data Index: 678217 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1006802 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1131. Min Act: -0.0001

Data Index: 227332 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1012. Min Act: -0.0001

Data Index: 584041 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0809. Min Act: -0.0001

Data Index: 674245 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1154227 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0808. Min Act: -0.0000

Data Index: 347647 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0641. Min Act: -0.0001

Data Index: 396661 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1118634 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1016786 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0653. Min Act: -0.0000

Data Index: 368332 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0566. Min Act: -0.0000

Data Index: 860574 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1334246 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0625. Min Act: -0.0001

Data Index: 416418 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0603. Min Act: -0.0001

Data Index: 770211 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0620. Min Act: -0.0001

Data Index: 82678 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0667. Min Act: -0.0000

Data Index: 704267 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0567. Min Act: -0.0001

Data Index: 686651 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0546. Min Act: -0.0000

Data Index: 927438 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.0545. Min Act: -0.0000

Data Index: 466500 (C4 (Web Text))

Max Activating Token Index: 136