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

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

Neuron 2419 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.9170. Min Act: -0.0000

Data Index: 638789 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.6542. Min Act: -0.0000

Data Index: 70711 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.5559. Min Act: -0.0000

Data Index: 1122743 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.4267. Min Act: -0.0000

Data Index: 162013 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.3944. Min Act: -0.0000

Data Index: 490978 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.3574. Min Act: -0.0000

Data Index: 239549 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.3218. Min Act: -0.0000

Data Index: 1058017 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.3255. Min Act: -0.0000

Data Index: 1255646 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.3032. Min Act: -0.0000

Data Index: 569141 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.3430. Min Act: -0.0000

Data Index: 205498 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.0766. Min Act: -0.0000

Data Index: 326634 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.2667. Min Act: -0.0000

Data Index: 809508 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.1334. Min Act: -0.0000

Data Index: 865135 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.0957. Min Act: -0.0000

Data Index: 679868 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 2.9170. Min Range: -2.9170

Max Act: 1.9942. Min Act: -0.0000

Data Index: 714607 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.0873. Min Act: -0.0000

Data Index: 104546 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 2.9170. Min Range: -2.9170

Max Act: 1.9698. Min Act: -0.0000

Data Index: 40447 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.0738. Min Act: -0.0000

Data Index: 1321831 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.1829. Min Act: -0.0000

Data Index: 519514 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 2.9170. Min Range: -2.9170

Max Act: 2.0446. Min Act: -0.0000

Data Index: 1126791 (C4 (Web Text))

Max Activating Token Index: 154