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

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

Neuron 1527 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: 3.6817. Min Range: -3.6817

Max Act: 3.6817. Min Act: -0.1700

Data Index: 1193280 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.5878. Min Act: -0.1700

Data Index: 336032 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.5878. Min Act: -0.1700

Data Index: 1252750 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.5878. Min Act: -0.1700

Data Index: 392838 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.5565. Min Act: -0.1700

Data Index: 1225831 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.5878. Min Act: -0.1700

Data Index: 827150 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.5251. Min Act: -0.1700

Data Index: 311054 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.5565. Min Act: -0.1700

Data Index: 5673 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.4938. Min Act: -0.1700

Data Index: 683843 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.5251. Min Act: -0.1700

Data Index: 1186643 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.5251. Min Act: -0.1700

Data Index: 175730 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.4938. Min Act: -0.1700

Data Index: 1273892 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.4938. Min Act: -0.1700

Data Index: 618647 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.4938. Min Act: -0.1700

Data Index: 70549 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.4938. Min Act: -0.1700

Data Index: 877720 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.4311. Min Act: -0.1700

Data Index: 1126323 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.4938. Min Act: -0.1700

Data Index: 754393 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.4624. Min Act: -0.1700

Data Index: 1188387 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.4938. Min Act: -0.1700

Data Index: 52706 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.4938. Min Act: -0.1700

Data Index: 483830 (C4 (Web Text))

Max Activating Token Index: 765