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

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

Neuron 1630 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2058. Min Act: -0.0002

Data Index: 584819 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2010. Min Act: -0.0002

Data Index: 349693 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2062. Min Act: -0.0002

Data Index: 564360 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2127. Min Act: -0.0002

Data Index: 1067150 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2127. Min Act: -0.0002

Data Index: 134156 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2046. Min Act: -0.0002

Data Index: 1059778 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1907. Min Act: -0.0001

Data Index: 503334 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1912. Min Act: -0.0002

Data Index: 332730 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1869. Min Act: -0.0002

Data Index: 160843 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1833. Min Act: -0.0002

Data Index: 542813 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1769. Min Act: -0.0002

Data Index: 1079515 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1334972 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1830. Min Act: -0.0002

Data Index: 165471 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1764. Min Act: -0.0001

Data Index: 613123 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1653. Min Act: -0.0002

Data Index: 1200185 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1616. Min Act: -0.0002

Data Index: 213853 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1667. Min Act: -0.0001

Data Index: 1138558 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1648. Min Act: -0.0002

Data Index: 510589 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1699. Min Act: -0.0002

Data Index: 1039455 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1583. Min Act: -0.0002

Data Index: 793874 (C4 (Web Text))

Max Activating Token Index: 230