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

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

Neuron 565 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: 5.2924. Min Range: -5.2924

Max Act: 5.2611. Min Act: -0.1699

Data Index: 919158 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 5.2924. Min Range: -5.2924

Max Act: 5.2924. Min Act: -0.1700

Data Index: 425901 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 5.2924. Min Range: -5.2924

Max Act: 5.1986. Min Act: -0.1700

Data Index: 973708 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 5.2924. Min Range: -5.2924

Max Act: 5.1674. Min Act: -0.1700

Data Index: 1072214 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 5.2924. Min Range: -5.2924

Max Act: 5.1674. Min Act: -0.1700

Data Index: 128780 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 5.2924. Min Range: -5.2924

Max Act: 5.1049. Min Act: -0.1674

Data Index: 1138517 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 5.2924. Min Range: -5.2924

Max Act: 5.1361. Min Act: -0.1699

Data Index: 1204001 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 5.2924. Min Range: -5.2924

Max Act: 5.0424. Min Act: -0.1700

Data Index: 414503 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 5.2924. Min Range: -5.2924

Max Act: 5.0424. Min Act: -0.1700

Data Index: 1009691 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 5.2924. Min Range: -5.2924

Max Act: 4.9799. Min Act: -0.1700

Data Index: 904995 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 5.2924. Min Range: -5.2924

Max Act: 4.9799. Min Act: -0.1699

Data Index: 903228 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 5.2924. Min Range: -5.2924

Max Act: 5.0111. Min Act: -0.1700

Data Index: 1186500 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 5.2924. Min Range: -5.2924

Max Act: 4.9486. Min Act: -0.1700

Data Index: 340396 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 5.2924. Min Range: -5.2924

Max Act: 4.9174. Min Act: -0.1700

Data Index: 744508 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 5.2924. Min Range: -5.2924

Max Act: 4.9486. Min Act: -0.1700

Data Index: 763893 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 5.2924. Min Range: -5.2924

Max Act: 4.8392. Min Act: -0.1700

Data Index: 284699 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 5.2924. Min Range: -5.2924

Max Act: 4.8861. Min Act: -0.1700

Data Index: 656339 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 5.2924. Min Range: -5.2924

Max Act: 4.8861. Min Act: -0.1699

Data Index: 57263 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 5.2924. Min Range: -5.2924

Max Act: 4.8392. Min Act: -0.1699

Data Index: 899255 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 5.2924. Min Range: -5.2924

Max Act: 4.8392. Min Act: -0.1700

Data Index: 808285 (C4 (Web Text))

Max Activating Token Index: 905