Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 104 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.1009. Min Range: -5.1009

Max Act: 5.1009. Min Act: -0.1700

Data Index: 1098665 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 5.1009. Min Range: -5.1009

Max Act: 5.0071. Min Act: -0.1700

Data Index: 911016 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 5.1009. Min Range: -5.1009

Max Act: 5.0696. Min Act: -0.1700

Data Index: 618723 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 5.1009. Min Range: -5.1009

Max Act: 5.0071. Min Act: -0.1700

Data Index: 891980 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9446. Min Act: -0.1700

Data Index: 61789 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9759. Min Act: -0.1700

Data Index: 220455 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9759. Min Act: -0.1700

Data Index: 490621 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9759. Min Act: -0.1700

Data Index: 68780 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9759. Min Act: -0.1700

Data Index: 641992 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9759. Min Act: -0.1700

Data Index: 7624 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9446. Min Act: -0.1700

Data Index: 136051 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9446. Min Act: -0.1700

Data Index: 343635 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9446. Min Act: -0.1700

Data Index: 564029 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9446. Min Act: -0.1700

Data Index: 104162 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9446. Min Act: -0.1700

Data Index: 578721 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9446. Min Act: -0.1700

Data Index: 284844 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9134. Min Act: -0.1700

Data Index: 369174 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9134. Min Act: -0.1700

Data Index: 301589 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9134. Min Act: -0.1700

Data Index: 392147 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 5.1009. Min Range: -5.1009

Max Act: 4.9134. Min Act: -0.1700

Data Index: 669554 (C4 (Web Text))

Max Activating Token Index: 11