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

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

Neuron 1784 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: 5.9467. Min Range: -5.9467

Max Act: 5.9467. Min Act: -0.1700

Data Index: 1088798 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.7904. Min Act: -0.1700

Data Index: 202919 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6654. Min Act: -0.1700

Data Index: 304710 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6342. Min Act: -0.1700

Data Index: 761020 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6342. Min Act: -0.1680

Data Index: 1044263 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6029. Min Act: -0.1700

Data Index: 458787 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.5717. Min Act: -0.1700

Data Index: 276495 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.5404. Min Act: -0.1700

Data Index: 202633 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.5404. Min Act: -0.1700

Data Index: 784946 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.5404. Min Act: -0.1700

Data Index: 117038 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.5404. Min Act: -0.1700

Data Index: 1293476 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.4779. Min Act: -0.1700

Data Index: 1105847 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.4779. Min Act: -0.1700

Data Index: 854869 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.4779. Min Act: -0.1699

Data Index: 799253 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.4779. Min Act: -0.1700

Data Index: 135878 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.4467. Min Act: -0.1700

Data Index: 1086344 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.4154. Min Act: -0.1700

Data Index: 450530 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.4467. Min Act: -0.1700

Data Index: 169994 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.4467. Min Act: -0.1700

Data Index: 294144 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.4154. Min Act: -0.1700

Data Index: 201091 (C4 (Web Text))

Max Activating Token Index: 977