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

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

Neuron 978 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.0825. Min Range: -3.0825

Max Act: 3.0825. Min Act: -0.1700

Data Index: 170610 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9877. Min Act: -0.1700

Data Index: 814360 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9877. Min Act: -0.1700

Data Index: 1183533 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9719. Min Act: -0.1700

Data Index: 323971 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9560. Min Act: -0.1700

Data Index: 5864 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9244. Min Act: -0.1700

Data Index: 1656158 (Python Code)

Max Activating Token Index: 502

Text #6

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9244. Min Act: -0.1700

Data Index: 879295 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9085. Min Act: -0.1700

Data Index: 261580 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9085. Min Act: -0.1700

Data Index: 512670 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9085. Min Act: -0.1700

Data Index: 1619358 (Python Code)

Max Activating Token Index: 851

Text #10

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9085. Min Act: -0.1700

Data Index: 17431 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.8768. Min Act: -0.1700

Data Index: 537579 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.8768. Min Act: -0.1700

Data Index: 829795 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9085. Min Act: -0.1700

Data Index: 1190445 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.9085. Min Act: -0.1700

Data Index: 88225 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.8926. Min Act: -0.1700

Data Index: 332407 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.8926. Min Act: -0.1700

Data Index: 874161 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.8768. Min Act: -0.1700

Data Index: 961494 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.8768. Min Act: -0.1700

Data Index: 1012642 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 3.0825. Min Range: -3.0825

Max Act: 2.8609. Min Act: -0.1700

Data Index: 394973 (C4 (Web Text))

Max Activating Token Index: 204