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

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

Neuron 1840 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: 8.0666. Min Range: -8.0666

Max Act: 7.9729. Min Act: -0.1700

Data Index: 899820 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 8.0666. Min Range: -8.0666

Max Act: 8.0666. Min Act: -0.1700

Data Index: 439986 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.9104. Min Act: -0.1700

Data Index: 258899 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.9104. Min Act: -0.1700

Data Index: 1069882 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.9104. Min Act: -0.1700

Data Index: 1296335 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.9104. Min Act: -0.1700

Data Index: 943762 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.8479. Min Act: -0.1700

Data Index: 165738 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.8479. Min Act: -0.1700

Data Index: 909150 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.8791. Min Act: -0.1700

Data Index: 1085306 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.8479. Min Act: -0.1700

Data Index: 64509 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.8166. Min Act: -0.1700

Data Index: 661999 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.9104. Min Act: -0.1700

Data Index: 571713 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.7229. Min Act: -0.1700

Data Index: 1267002 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.7541. Min Act: -0.1700

Data Index: 323141 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.7229. Min Act: -0.1700

Data Index: 781412 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.7854. Min Act: -0.1699

Data Index: 334779 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.7229. Min Act: -0.1700

Data Index: 89212 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.6604. Min Act: -0.1700

Data Index: 964406 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.6916. Min Act: -0.1700

Data Index: 1113544 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 8.0666. Min Range: -8.0666

Max Act: 7.6604. Min Act: -0.1700

Data Index: 758221 (C4 (Web Text))

Max Activating Token Index: 190