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

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

Neuron 1901 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: 5.2517. Min Range: -5.2517

Max Act: 5.2517. Min Act: -0.1700

Data Index: 1035184 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 5.2517. Min Range: -5.2517

Max Act: 5.1892. Min Act: -0.1700

Data Index: 1006980 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 5.2517. Min Range: -5.2517

Max Act: 5.0955. Min Act: -0.1700

Data Index: 15114 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 5.2517. Min Range: -5.2517

Max Act: 5.0330. Min Act: -0.1700

Data Index: 951116 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 5.2517. Min Range: -5.2517

Max Act: 5.0017. Min Act: -0.1700

Data Index: 681510 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.9705. Min Act: -0.1700

Data Index: 1026966 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.9705. Min Act: -0.1700

Data Index: 761215 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.8767. Min Act: -0.1700

Data Index: 579551 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.8455. Min Act: -0.1700

Data Index: 647995 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.8767. Min Act: -0.1700

Data Index: 693654 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.8455. Min Act: -0.1700

Data Index: 570333 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.8767. Min Act: -0.1700

Data Index: 169483 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.8142. Min Act: -0.1700

Data Index: 880241 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.8142. Min Act: -0.1700

Data Index: 765407 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.7829. Min Act: -0.1700

Data Index: 1250264 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.7829. Min Act: -0.1700

Data Index: 889784 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.8142. Min Act: -0.1700

Data Index: 431002 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.8142. Min Act: -0.1699

Data Index: 423506 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.7829. Min Act: -0.1700

Data Index: 1182356 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 5.2517. Min Range: -5.2517

Max Act: 4.7517. Min Act: -0.1700

Data Index: 1115522 (C4 (Web Text))

Max Activating Token Index: 987