Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4181 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5709. Min Range: -2.5709

Max Act: 2.5709. Min Act: -0.0000

Data Index: 1098640 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 2.5709. Min Range: -2.5709

Max Act: 2.1954. Min Act: -0.0000

Data Index: 440718 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 2.5709. Min Range: -2.5709

Max Act: 2.0483. Min Act: -0.0000

Data Index: 1031282 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.8368. Min Act: -0.0000

Data Index: 843756 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.8094. Min Act: -0.0000

Data Index: 696123 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.8979. Min Act: -0.0000

Data Index: 969525 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.9779. Min Act: -0.0000

Data Index: 561599 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.8114. Min Act: -0.0000

Data Index: 980137 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.8082. Min Act: -0.0000

Data Index: 1316140 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.6976. Min Act: -0.0000

Data Index: 1121797 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.9082. Min Act: -0.0000

Data Index: 1050246 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.7914. Min Act: -0.0000

Data Index: 932390 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.7745. Min Act: -0.0000

Data Index: 1235297 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.7932. Min Act: -0.0000

Data Index: 475964 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.6644. Min Act: -0.0000

Data Index: 629831 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.7263. Min Act: -0.0000

Data Index: 276913 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.7292. Min Act: -0.0000

Data Index: 690599 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.6691. Min Act: -0.0000

Data Index: 123688 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.5807. Min Act: -0.0000

Data Index: 1108984 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 2.5709. Min Range: -2.5709

Max Act: 1.7200. Min Act: -0.0000

Data Index: 71343 (C4 (Web Text))

Max Activating Token Index: 690