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

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

Neuron 799 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: 3.4701. Min Range: -3.4701

Max Act: 3.4701. Min Act: -0.1700

Data Index: 727892 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.4701. Min Act: -0.1700

Data Index: 327204 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.3917. Min Act: -0.1700

Data Index: 418505 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.3761. Min Act: -0.1700

Data Index: 1135082 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.3917. Min Act: -0.1700

Data Index: 302820 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.3604. Min Act: -0.1700

Data Index: 882891 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.3761. Min Act: -0.1700

Data Index: 542777 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.3917. Min Act: -0.1698

Data Index: 675988 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.3447. Min Act: -0.1700

Data Index: 1359329 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.2976. Min Act: -0.1700

Data Index: 297989 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.2976. Min Act: -0.1700

Data Index: 168949 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.2347. Min Act: -0.1700

Data Index: 584323 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.2819. Min Act: -0.1700

Data Index: 381107 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.2661. Min Act: -0.1699

Data Index: 1171233 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.2819. Min Act: -0.1700

Data Index: 475101 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.2661. Min Act: -0.1700

Data Index: 1178598 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.2504. Min Act: -0.1699

Data Index: 1316575 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.2504. Min Act: -0.1700

Data Index: 1153791 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.2190. Min Act: -0.1700

Data Index: 1176823 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 3.4701. Min Range: -3.4701

Max Act: 3.2347. Min Act: -0.1699

Data Index: 752655 (C4 (Web Text))

Max Activating Token Index: 1008