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

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

Neuron 1879 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.9014. Min Act: -0.1700

Data Index: 322339 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7763. Min Act: -0.1700

Data Index: 1103947 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7763. Min Act: -0.1700

Data Index: 960224 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7450. Min Act: -0.1700

Data Index: 451006 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.6511. Min Act: -0.1700

Data Index: 1117408 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.6824. Min Act: -0.1700

Data Index: 1235727 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.6511. Min Act: -0.1700

Data Index: 382876 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.6198. Min Act: -0.1700

Data Index: 760167 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.6511. Min Act: -0.1700

Data Index: 146478 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.6198. Min Act: -0.1700

Data Index: 912417 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.6511. Min Act: -0.1700

Data Index: 1076370 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.6511. Min Act: -0.1700

Data Index: 54788 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.6198. Min Act: -0.1700

Data Index: 491871 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.5885. Min Act: -0.1700

Data Index: 709198 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.5885. Min Act: -0.1700

Data Index: 237103 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.5572. Min Act: -0.1700

Data Index: 677307 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.5728. Min Act: -0.1700

Data Index: 91618 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.5885. Min Act: -0.1700

Data Index: 716221 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.6198. Min Act: -0.1700

Data Index: 255392 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.5572. Min Act: -0.1700

Data Index: 990558 (C4 (Web Text))

Max Activating Token Index: 1000