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

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

Neuron 1863 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: 3.2098. Min Range: -3.2098

Max Act: 3.2098. Min Act: -0.1700

Data Index: 1081906 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 3.2098. Min Range: -3.2098

Max Act: 3.1783. Min Act: -0.1700

Data Index: 344743 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 3.2098. Min Range: -3.2098

Max Act: 3.1468. Min Act: -0.1700

Data Index: 472124 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 3.2098. Min Range: -3.2098

Max Act: 3.1783. Min Act: -0.1700

Data Index: 1012720 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 3.2098. Min Range: -3.2098

Max Act: 3.0838. Min Act: -0.1700

Data Index: 1310713 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 3.2098. Min Range: -3.2098

Max Act: 3.0680. Min Act: -0.1700

Data Index: 1098762 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 3.2098. Min Range: -3.2098

Max Act: 3.0522. Min Act: -0.1700

Data Index: 501169 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 3.2098. Min Range: -3.2098

Max Act: 2.9732. Min Act: -0.1700

Data Index: 252314 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 3.2098. Min Range: -3.2098

Max Act: 3.0049. Min Act: -0.1700

Data Index: 1044164 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 3.2098. Min Range: -3.2098

Max Act: 2.9732. Min Act: -0.1700

Data Index: 250769 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 3.2098. Min Range: -3.2098

Max Act: 2.9890. Min Act: -0.1700

Data Index: 672408 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 3.2098. Min Range: -3.2098

Max Act: 3.0049. Min Act: -0.1700

Data Index: 251789 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 3.2098. Min Range: -3.2098

Max Act: 2.9732. Min Act: -0.1700

Data Index: 306520 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 3.2098. Min Range: -3.2098

Max Act: 3.0049. Min Act: -0.1700

Data Index: 919164 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 3.2098. Min Range: -3.2098

Max Act: 3.0365. Min Act: -0.1700

Data Index: 860567 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 3.2098. Min Range: -3.2098

Max Act: 2.9732. Min Act: -0.1700

Data Index: 1195012 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 3.2098. Min Range: -3.2098

Max Act: 2.9732. Min Act: -0.1700

Data Index: 949691 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 3.2098. Min Range: -3.2098

Max Act: 2.9732. Min Act: -0.1700

Data Index: 220644 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 3.2098. Min Range: -3.2098

Max Act: 2.9732. Min Act: -0.1700

Data Index: 437158 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 3.2098. Min Range: -3.2098

Max Act: 2.9732. Min Act: -0.1700

Data Index: 650732 (C4 (Web Text))

Max Activating Token Index: 532