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

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

Neuron 1562 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: 4.1007. Min Range: -4.1007

Max Act: 4.1007. Min Act: -0.1700

Data Index: 701057 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.9757. Min Act: -0.1700

Data Index: 942438 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8819. Min Act: -0.1700

Data Index: 785607 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8819. Min Act: -0.1700

Data Index: 753686 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8506. Min Act: -0.1700

Data Index: 229296 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8819. Min Act: -0.1700

Data Index: 158304 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8506. Min Act: -0.1700

Data Index: 276635 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8506. Min Act: -0.1700

Data Index: 295842 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8506. Min Act: -0.1700

Data Index: 686482 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8193. Min Act: -0.1700

Data Index: 379133 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8506. Min Act: -0.1700

Data Index: 784677 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8193. Min Act: -0.1700

Data Index: 320896 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.7880. Min Act: -0.1700

Data Index: 909523 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8193. Min Act: -0.1700

Data Index: 1327570 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.7567. Min Act: -0.1700

Data Index: 760414 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.7567. Min Act: -0.1700

Data Index: 655483 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.7880. Min Act: -0.1700

Data Index: 765805 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.7567. Min Act: -0.1700

Data Index: 382515 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.8193. Min Act: -0.1700

Data Index: 913812 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 4.1007. Min Range: -4.1007

Max Act: 3.7880. Min Act: -0.1700

Data Index: 205669 (C4 (Web Text))

Max Activating Token Index: 338