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

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

Neuron 669 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.3041. Min Act: -0.1700

Data Index: 425018 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.2570. Min Act: -0.1700

Data Index: 232696 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.2098. Min Act: -0.1700

Data Index: 1273493 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.1941. Min Act: -0.1700

Data Index: 1302322 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.1626. Min Act: -0.1700

Data Index: 1100184 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0996. Min Act: -0.1700

Data Index: 1266908 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0838. Min Act: -0.1700

Data Index: 187940 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0048. Min Act: -0.1700

Data Index: 434120 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0522. Min Act: -0.1700

Data Index: 402590 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0364. Min Act: -0.1700

Data Index: 178152 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0522. Min Act: -0.1700

Data Index: 910440 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0206. Min Act: -0.1700

Data Index: 206976 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0206. Min Act: -0.1700

Data Index: 86788 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0206. Min Act: -0.1700

Data Index: 794133 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0364. Min Act: -0.1700

Data Index: 1067009 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0364. Min Act: -0.1700

Data Index: 1137861 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0206. Min Act: -0.1700

Data Index: 384635 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0206. Min Act: -0.1700

Data Index: 820372 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0206. Min Act: -0.1700

Data Index: 1000848 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 3.3041. Min Range: -3.3041

Max Act: 3.0206. Min Act: -0.1700

Data Index: 459017 (C4 (Web Text))

Max Activating Token Index: 802