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

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

Neuron 1721 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.9408. Min Act: -0.1700

Data Index: 766613 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.9408. Min Act: -0.1700

Data Index: 333168 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.9095. Min Act: -0.1700

Data Index: 112449 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.8470. Min Act: -0.1700

Data Index: 335034 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.8783. Min Act: -0.1700

Data Index: 641109 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.8157. Min Act: -0.1700

Data Index: 359629 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.8470. Min Act: -0.1700

Data Index: 1214294 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.8470. Min Act: -0.1700

Data Index: 324494 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.8783. Min Act: -0.1700

Data Index: 434509 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.8157. Min Act: -0.1700

Data Index: 1060439 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.7844. Min Act: -0.1700

Data Index: 1092444 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.8470. Min Act: -0.1700

Data Index: 1077507 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.7844. Min Act: -0.1700

Data Index: 559044 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.7844. Min Act: -0.1700

Data Index: 1076486 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.7844. Min Act: -0.1700

Data Index: 180821 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.7844. Min Act: -0.1700

Data Index: 299377 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.7844. Min Act: -0.1700

Data Index: 436693 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.7844. Min Act: -0.1700

Data Index: 283846 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.7844. Min Act: -0.1700

Data Index: 1059908 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 3.9408. Min Range: -3.9408

Max Act: 3.8157. Min Act: -0.1700

Data Index: 912554 (C4 (Web Text))

Max Activating Token Index: 652