Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 323 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.3625. Min Act: -0.1700

Data Index: 308094 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.2375. Min Act: -0.1700

Data Index: 65913 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.2062. Min Act: -0.1700

Data Index: 1009643 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.0812. Min Act: -0.1700

Data Index: 582239 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.1750. Min Act: -0.1700

Data Index: 351757 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.2062. Min Act: -0.1700

Data Index: 1204976 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.1437. Min Act: -0.1700

Data Index: 539089 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.1125. Min Act: -0.1700

Data Index: 339942 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.0812. Min Act: -0.1700

Data Index: 26198 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.0812. Min Act: -0.1700

Data Index: 948670 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.0500. Min Act: -0.1700

Data Index: 1077050 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.0500. Min Act: -0.1700

Data Index: 773403 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.0187. Min Act: -0.1700

Data Index: 762929 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.0500. Min Act: -0.1700

Data Index: 589331 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.0187. Min Act: -0.1700

Data Index: 158218 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.0812. Min Act: -0.1700

Data Index: 255263 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 5.3625. Min Range: -5.3625

Max Act: 4.9562. Min Act: -0.1700

Data Index: 1124000 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 5.3625. Min Range: -5.3625

Max Act: 5.0500. Min Act: -0.1700

Data Index: 924092 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 5.3625. Min Range: -5.3625

Max Act: 4.9875. Min Act: -0.1700

Data Index: 501501 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 5.3625. Min Range: -5.3625

Max Act: 4.9875. Min Act: -0.1700

Data Index: 1086113 (C4 (Web Text))

Max Activating Token Index: 581