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

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

Neuron 1596 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: 3.2466. Min Range: -3.2466

Max Act: 3.2466. Min Act: -0.1700

Data Index: 769533 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.2466. Min Act: -0.1700

Data Index: 1037097 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.2309. Min Act: -0.1700

Data Index: 987709 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.2151. Min Act: -0.1700

Data Index: 427023 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.2309. Min Act: -0.1700

Data Index: 719921 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1994. Min Act: -0.1700

Data Index: 707199 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1994. Min Act: -0.1700

Data Index: 557411 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1994. Min Act: -0.1700

Data Index: 963825 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1837. Min Act: -0.1700

Data Index: 1246166 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1679. Min Act: -0.1700

Data Index: 12950 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1679. Min Act: -0.1700

Data Index: 667600 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1679. Min Act: -0.1700

Data Index: 98894 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1522. Min Act: -0.1700

Data Index: 439443 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1522. Min Act: -0.1700

Data Index: 577570 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1679. Min Act: -0.1700

Data Index: 464097 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1679. Min Act: -0.1700

Data Index: 273785 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1837. Min Act: -0.1700

Data Index: 548740 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1522. Min Act: -0.1700

Data Index: 1305507 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1522. Min Act: -0.1700

Data Index: 1287004 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 3.2466. Min Range: -3.2466

Max Act: 3.1522. Min Act: -0.1700

Data Index: 741032 (C4 (Web Text))

Max Activating Token Index: 607