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

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

Neuron 1644 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: 3.6640. Min Range: -3.6640

Max Act: 3.6640. Min Act: -0.1700

Data Index: 1087443 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.6640. Min Act: -0.1700

Data Index: 444493 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.6327. Min Act: -0.1700

Data Index: 1355159 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.6327. Min Act: -0.1700

Data Index: 1249451 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.6327. Min Act: -0.1700

Data Index: 679386 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.6014. Min Act: -0.1700

Data Index: 1286167 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.6014. Min Act: -0.1700

Data Index: 736571 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5700. Min Act: -0.1700

Data Index: 1083653 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5700. Min Act: -0.1700

Data Index: 76522 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.6014. Min Act: -0.1700

Data Index: 1108886 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5074. Min Act: -0.1700

Data Index: 1277267 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5074. Min Act: -0.1700

Data Index: 583451 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5700. Min Act: -0.1700

Data Index: 1223727 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5387. Min Act: -0.1700

Data Index: 1214727 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5387. Min Act: -0.1700

Data Index: 274098 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5387. Min Act: -0.1700

Data Index: 296037 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5700. Min Act: -0.1700

Data Index: 418759 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5074. Min Act: -0.1700

Data Index: 1160225 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5387. Min Act: -0.1700

Data Index: 379609 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4760. Min Act: -0.1700

Data Index: 223344 (C4 (Web Text))

Max Activating Token Index: 835