Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 751 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.6044. Min Act: -0.1700

Data Index: 921244 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.5732. Min Act: -0.1700

Data Index: 1321150 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.5419. Min Act: -0.1700

Data Index: 260873 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.5107. Min Act: -0.1700

Data Index: 1016271 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.4169. Min Act: -0.1700

Data Index: 756404 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.4794. Min Act: -0.1700

Data Index: 1111617 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.4169. Min Act: -0.1700

Data Index: 1130152 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.3857. Min Act: -0.1700

Data Index: 1129671 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.3544. Min Act: -0.1700

Data Index: 740147 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.3857. Min Act: -0.1700

Data Index: 1112719 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.3232. Min Act: -0.1700

Data Index: 1000321 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.3232. Min Act: -0.1700

Data Index: 93824 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.3232. Min Act: -0.1700

Data Index: 971106 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.3857. Min Act: -0.1700

Data Index: 1013801 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.2607. Min Act: -0.1700

Data Index: 20907 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.3232. Min Act: -0.1700

Data Index: 964751 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.2919. Min Act: -0.1700

Data Index: 768768 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.3232. Min Act: -0.1700

Data Index: 202540 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.2919. Min Act: -0.1700

Data Index: 189800 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 5.6044. Min Range: -5.6044

Max Act: 5.2919. Min Act: -0.1700

Data Index: 971876 (C4 (Web Text))

Max Activating Token Index: 431