Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 2008 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.0783. Min Range: -2.0783

Max Act: 2.0783. Min Act: -0.1700

Data Index: 622354 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 2.0783. Min Range: -2.0783

Max Act: 2.0525. Min Act: -0.1700

Data Index: 174430 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 2.0783. Min Range: -2.0783

Max Act: 2.0512. Min Act: -0.1700

Data Index: 630209 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 2.0783. Min Range: -2.0783

Max Act: 2.0521. Min Act: -0.1700

Data Index: 959101 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 2.0783. Min Range: -2.0783

Max Act: 2.0446. Min Act: -0.1700

Data Index: 298549 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 2.0783. Min Range: -2.0783

Max Act: 2.0071. Min Act: -0.1700

Data Index: 455967 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9853. Min Act: -0.1700

Data Index: 210105 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9543. Min Act: -0.1700

Data Index: 85317 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9532. Min Act: -0.1700

Data Index: 364160 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9478. Min Act: -0.1700

Data Index: 235001 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9456. Min Act: -0.1700

Data Index: 535695 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9498. Min Act: -0.1700

Data Index: 136927 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9403. Min Act: -0.1700

Data Index: 1232734 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9369. Min Act: -0.1700

Data Index: 240539 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9295. Min Act: -0.1700

Data Index: 963411 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9304. Min Act: -0.1700

Data Index: 827054 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9255. Min Act: -0.1700

Data Index: 17796 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9202. Min Act: -0.1700

Data Index: 960213 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9219. Min Act: -0.1700

Data Index: 675640 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 2.0783. Min Range: -2.0783

Max Act: 1.9204. Min Act: -0.1700

Data Index: 639785 (C4 (Web Text))

Max Activating Token Index: 956