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

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

Neuron 1641 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.9672. Min Act: -0.1700

Data Index: 630126 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.9360. Min Act: -0.1700

Data Index: 1038477 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.9047. Min Act: -0.1700

Data Index: 977382 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.9047. Min Act: -0.1700

Data Index: 312297 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8891. Min Act: -0.1700

Data Index: 387623 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8734. Min Act: -0.1700

Data Index: 226228 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8578. Min Act: -0.1700

Data Index: 18551 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8578. Min Act: -0.1700

Data Index: 81039 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8578. Min Act: -0.1700

Data Index: 889076 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8421. Min Act: -0.1700

Data Index: 1048871 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8265. Min Act: -0.1700

Data Index: 341833 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8421. Min Act: -0.1700

Data Index: 984035 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8265. Min Act: -0.1700

Data Index: 961170 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8265. Min Act: -0.1700

Data Index: 39489 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8421. Min Act: -0.1700

Data Index: 1146752 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8421. Min Act: -0.1700

Data Index: 639096 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8421. Min Act: -0.1700

Data Index: 496572 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8421. Min Act: -0.1700

Data Index: 567090 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8265. Min Act: -0.1700

Data Index: 1087552 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 3.9672. Min Range: -3.9672

Max Act: 3.8265. Min Act: -0.1700

Data Index: 86325 (C4 (Web Text))

Max Activating Token Index: 20