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

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

Neuron 1735 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.3234. Min Range: -8.3234

Max Act: 8.3234. Min Act: -0.1700

Data Index: 805567 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 8.3234. Min Range: -8.3234

Max Act: 8.1984. Min Act: -0.1700

Data Index: 430011 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.9484. Min Act: -0.1700

Data Index: 307766 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.8859. Min Act: -0.1700

Data Index: 1273147 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.8234. Min Act: -0.1700

Data Index: 753335 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.7609. Min Act: -0.1700

Data Index: 386368 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.6359. Min Act: -0.1700

Data Index: 632982 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.6359. Min Act: -0.1700

Data Index: 977497 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.6359. Min Act: -0.1700

Data Index: 1254136 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.5734. Min Act: -0.1700

Data Index: 1137799 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.5109. Min Act: -0.1700

Data Index: 316613 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.6359. Min Act: -0.1700

Data Index: 866246 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.5109. Min Act: -0.1700

Data Index: 1310634 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.5734. Min Act: -0.1700

Data Index: 270510 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.5109. Min Act: -0.1700

Data Index: 651510 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.4484. Min Act: -0.1700

Data Index: 84019 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.5109. Min Act: -0.1699

Data Index: 330314 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.4484. Min Act: -0.1700

Data Index: 1210263 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.4484. Min Act: -0.1700

Data Index: 354673 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 8.3234. Min Range: -8.3234

Max Act: 7.4484. Min Act: -0.1700

Data Index: 575741 (C4 (Web Text))

Max Activating Token Index: 13