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

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

Neuron 1421 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0950. Min Range: -7.0950

Max Act: 7.0950. Min Act: -0.1700

Data Index: 278911 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.8450. Min Act: -0.1700

Data Index: 328785 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.7825. Min Act: -0.1700

Data Index: 667437 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.7825. Min Act: -0.1700

Data Index: 295264 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.7825. Min Act: -0.1700

Data Index: 1182530 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.7512. Min Act: -0.1700

Data Index: 463180 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.8137. Min Act: -0.1700

Data Index: 359679 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.7825. Min Act: -0.1700

Data Index: 1273207 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.7825. Min Act: -0.1700

Data Index: 704250 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.7825. Min Act: -0.1700

Data Index: 829388 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.7512. Min Act: -0.1700

Data Index: 762909 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.7200. Min Act: -0.1700

Data Index: 536096 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.6262. Min Act: -0.1700

Data Index: 631790 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.6887. Min Act: -0.1700

Data Index: 50756 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.6262. Min Act: -0.1700

Data Index: 42647 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.6575. Min Act: -0.1700

Data Index: 1071854 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.7200. Min Act: -0.1700

Data Index: 646297 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.6887. Min Act: -0.1700

Data Index: 1181330 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.6575. Min Act: -0.1700

Data Index: 901094 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 7.0950. Min Range: -7.0950

Max Act: 6.6575. Min Act: -0.1700

Data Index: 307620 (C4 (Web Text))

Max Activating Token Index: 46