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

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

Neuron 163 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: 5.6746. Min Range: -5.6746

Max Act: 5.6746. Min Act: -0.1700

Data Index: 1039068 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.6433. Min Act: -0.1700

Data Index: 532207 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.6121. Min Act: -0.1700

Data Index: 1305205 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.5496. Min Act: -0.1700

Data Index: 190297 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4871. Min Act: -0.1700

Data Index: 1137316 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.5496. Min Act: -0.1700

Data Index: 1012840 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4871. Min Act: -0.1700

Data Index: 1030155 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4246. Min Act: -0.1700

Data Index: 1017580 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4871. Min Act: -0.1700

Data Index: 978364 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4871. Min Act: -0.1700

Data Index: 119072 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.3933. Min Act: -0.1700

Data Index: 1229240 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4246. Min Act: -0.1700

Data Index: 138017 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4246. Min Act: -0.1700

Data Index: 234056 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.3933. Min Act: -0.1700

Data Index: 480717 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4246. Min Act: -0.1700

Data Index: 92947 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.3933. Min Act: -0.1700

Data Index: 1100448 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4246. Min Act: -0.1700

Data Index: 104985 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4558. Min Act: -0.1699

Data Index: 594840 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4246. Min Act: -0.1700

Data Index: 1214949 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 5.6746. Min Range: -5.6746

Max Act: 5.4558. Min Act: -0.1700

Data Index: 1000655 (C4 (Web Text))

Max Activating Token Index: 333