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

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

Neuron 268 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7765. Min Range: -5.7765

Max Act: 5.7765. Min Act: -0.1700

Data Index: 360464 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 5.7765. Min Range: -5.7765

Max Act: 5.4640. Min Act: -0.1700

Data Index: 766844 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 5.7765. Min Range: -5.7765

Max Act: 5.3703. Min Act: -0.1700

Data Index: 292289 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 5.7765. Min Range: -5.7765

Max Act: 5.3390. Min Act: -0.1700

Data Index: 450951 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 5.7765. Min Range: -5.7765

Max Act: 5.2765. Min Act: -0.1700

Data Index: 905449 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 5.7765. Min Range: -5.7765

Max Act: 5.1203. Min Act: -0.1700

Data Index: 836468 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 5.7765. Min Range: -5.7765

Max Act: 5.1203. Min Act: -0.1700

Data Index: 1162608 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 5.7765. Min Range: -5.7765

Max Act: 5.0578. Min Act: -0.1700

Data Index: 1256653 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 5.7765. Min Range: -5.7765

Max Act: 5.0578. Min Act: -0.1700

Data Index: 1091064 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 5.7765. Min Range: -5.7765

Max Act: 5.0265. Min Act: -0.1700

Data Index: 1304987 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 5.7765. Min Range: -5.7765

Max Act: 5.0578. Min Act: -0.1700

Data Index: 896732 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 5.7765. Min Range: -5.7765

Max Act: 4.9953. Min Act: -0.1700

Data Index: 68507 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 5.7765. Min Range: -5.7765

Max Act: 4.9640. Min Act: -0.1700

Data Index: 458654 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 5.7765. Min Range: -5.7765

Max Act: 4.9953. Min Act: -0.1619

Data Index: 718030 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 5.7765. Min Range: -5.7765

Max Act: 4.9953. Min Act: -0.1700

Data Index: 1189824 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 5.7765. Min Range: -5.7765

Max Act: 4.9328. Min Act: -0.1700

Data Index: 803220 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 5.7765. Min Range: -5.7765

Max Act: 4.9640. Min Act: -0.1700

Data Index: 251877 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 5.7765. Min Range: -5.7765

Max Act: 4.9328. Min Act: -0.1700

Data Index: 606915 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 5.7765. Min Range: -5.7765

Max Act: 4.9015. Min Act: -0.1700

Data Index: 733626 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 5.7765. Min Range: -5.7765

Max Act: 4.9015. Min Act: -0.1700

Data Index: 1068660 (C4 (Web Text))

Max Activating Token Index: 413