Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 728 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.9090. Min Act: -0.1698

Data Index: 1124621 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.8621. Min Act: -0.1700

Data Index: 100683 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.8308. Min Act: -0.1700

Data Index: 230260 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7996. Min Act: -0.1700

Data Index: 668855 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7839. Min Act: -0.1700

Data Index: 496082 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7683. Min Act: -0.1700

Data Index: 580963 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7996. Min Act: -0.1700

Data Index: 924408 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7370. Min Act: -0.1700

Data Index: 1139389 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7526. Min Act: -0.1700

Data Index: 574448 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7370. Min Act: -0.1700

Data Index: 1280747 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7370. Min Act: -0.1700

Data Index: 1236966 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7526. Min Act: -0.1700

Data Index: 1036509 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7057. Min Act: -0.1700

Data Index: 345927 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7370. Min Act: -0.1700

Data Index: 1224353 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7057. Min Act: -0.1700

Data Index: 376258 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7370. Min Act: -0.1700

Data Index: 762743 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7213. Min Act: -0.1700

Data Index: 282654 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.6900. Min Act: -0.1700

Data Index: 1083455 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7057. Min Act: -0.1700

Data Index: 511981 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 3.9090. Min Range: -3.9090

Max Act: 3.7213. Min Act: -0.1700

Data Index: 1264958 (C4 (Web Text))

Max Activating Token Index: 774