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

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

Neuron 1149 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.8509. Min Act: -0.1700

Data Index: 711138 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.7884. Min Act: -0.1700

Data Index: 104120 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.8196. Min Act: -0.1700

Data Index: 469671 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.7259. Min Act: -0.1700

Data Index: 96231 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.6321. Min Act: -0.1700

Data Index: 183517 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.6009. Min Act: -0.1700

Data Index: 1067712 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.6634. Min Act: -0.1700

Data Index: 725500 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.6009. Min Act: -0.1700

Data Index: 1011331 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.5696. Min Act: -0.1700

Data Index: 487388 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.6321. Min Act: -0.1700

Data Index: 84628 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.5696. Min Act: -0.1700

Data Index: 134815 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.6321. Min Act: -0.1700

Data Index: 421432 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.6009. Min Act: -0.1700

Data Index: 351993 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.5384. Min Act: -0.1700

Data Index: 674809 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.4759. Min Act: -0.1700

Data Index: 1274021 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.5696. Min Act: -0.1700

Data Index: 1202951 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.5696. Min Act: -0.1700

Data Index: 69532 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.5384. Min Act: -0.1700

Data Index: 983628 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.5071. Min Act: -0.1700

Data Index: 75757 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 5.8509. Min Range: -5.8509

Max Act: 5.4759. Min Act: -0.1700

Data Index: 1129486 (C4 (Web Text))

Max Activating Token Index: 602