Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5105 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1777. Min Range: -2.1777

Max Act: 2.1777. Min Act: -0.0000

Data Index: 1166775 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 2.1777. Min Range: -2.1777

Max Act: 2.1202. Min Act: -0.0000

Data Index: 1053945 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.8621. Min Act: -0.0000

Data Index: 641216 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.7659. Min Act: -0.0000

Data Index: 115741 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.7406. Min Act: -0.0000

Data Index: 1395325 (Python Code)

Max Activating Token Index: 290

Text #5

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.8562. Min Act: -0.0000

Data Index: 656484 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.7894. Min Act: -0.0000

Data Index: 129276 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.6778. Min Act: -0.0000

Data Index: 622376 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.7247. Min Act: -0.0000

Data Index: 319001 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.8030. Min Act: -0.0000

Data Index: 1307711 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.6690. Min Act: -0.0000

Data Index: 168104 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.5680. Min Act: -0.0000

Data Index: 5447 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.7436. Min Act: -0.0000

Data Index: 264533 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.6493. Min Act: -0.0000

Data Index: 609208 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.6528. Min Act: -0.0000

Data Index: 859753 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.7202. Min Act: -0.0000

Data Index: 269516 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.6229. Min Act: -0.0000

Data Index: 988128 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.6021. Min Act: -0.0000

Data Index: 1419603 (Python Code)

Max Activating Token Index: 709

Text #18

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.5984. Min Act: -0.0000

Data Index: 475457 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 2.1777. Min Range: -2.1777

Max Act: 1.5187. Min Act: -0.0000

Data Index: 533466 (C4 (Web Text))

Max Activating Token Index: 403