Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1781 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.6707. Min Act: -0.1700

Data Index: 214640 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.5767. Min Act: -0.1700

Data Index: 476844 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.5141. Min Act: -0.1700

Data Index: 29043 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4827. Min Act: -0.1700

Data Index: 924344 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4984. Min Act: -0.1700

Data Index: 71898 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4357. Min Act: -0.1700

Data Index: 1354016 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3887. Min Act: -0.1700

Data Index: 210067 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3573. Min Act: -0.1700

Data Index: 617262 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3573. Min Act: -0.1700

Data Index: 515454 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3259. Min Act: -0.1700

Data Index: 818951 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3259. Min Act: -0.1700

Data Index: 679919 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.2788. Min Act: -0.1700

Data Index: 966265 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3102. Min Act: -0.1700

Data Index: 1052033 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.2788. Min Act: -0.1700

Data Index: 246989 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.2631. Min Act: -0.1700

Data Index: 795498 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.2316. Min Act: -0.1700

Data Index: 1246658 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.2474. Min Act: -0.1700

Data Index: 925372 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.2316. Min Act: -0.1700

Data Index: 2547 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.2159. Min Act: -0.1700

Data Index: 775687 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.2159. Min Act: -0.1700

Data Index: 706181 (C4 (Web Text))

Max Activating Token Index: 50