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

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

Neuron 948 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.9488. Min Act: -0.1700

Data Index: 535655 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8862. Min Act: -0.1700

Data Index: 815764 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.9175. Min Act: -0.1700

Data Index: 446097 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8706. Min Act: -0.1700

Data Index: 12168 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8237. Min Act: -0.1700

Data Index: 1117471 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8549. Min Act: -0.1700

Data Index: 84590 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8237. Min Act: -0.1700

Data Index: 1157991 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.8237. Min Act: -0.1700

Data Index: 416259 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7924. Min Act: -0.1700

Data Index: 420443 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7924. Min Act: -0.1700

Data Index: 482063 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7298. Min Act: -0.1700

Data Index: 930464 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7611. Min Act: -0.1700

Data Index: 141571 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7454. Min Act: -0.1700

Data Index: 1072570 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7454. Min Act: -0.1700

Data Index: 656516 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7142. Min Act: -0.1700

Data Index: 718019 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7142. Min Act: -0.1700

Data Index: 102675 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7454. Min Act: -0.1700

Data Index: 1300316 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.6985. Min Act: -0.1700

Data Index: 488119 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7142. Min Act: -0.1700

Data Index: 195887 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7142. Min Act: -0.1700

Data Index: 504972 (C4 (Web Text))

Max Activating Token Index: 519