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

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

Neuron 822 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.5824. Min Act: -0.1700

Data Index: 240552 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.5824. Min Act: -0.1700

Data Index: 1613597 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.5510. Min Act: -0.1700

Data Index: 806523 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.5667. Min Act: -0.1700

Data Index: 779810 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.5824. Min Act: -0.1700

Data Index: 986539 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.5040. Min Act: -0.1700

Data Index: 225603 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.5197. Min Act: -0.1700

Data Index: 97080 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4727. Min Act: -0.1700

Data Index: 144798 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4884. Min Act: -0.1700

Data Index: 555305 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4884. Min Act: -0.1700

Data Index: 1328478 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4570. Min Act: -0.1700

Data Index: 1436015 (Python Code)

Max Activating Token Index: 618

Text #11

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4727. Min Act: -0.1700

Data Index: 860478 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4884. Min Act: -0.1700

Data Index: 1278238 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4727. Min Act: -0.1700

Data Index: 1209053 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4413. Min Act: -0.1700

Data Index: 1068908 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4570. Min Act: -0.1700

Data Index: 453964 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4727. Min Act: -0.1700

Data Index: 906997 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4570. Min Act: -0.1700

Data Index: 775921 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4727. Min Act: -0.1700

Data Index: 550050 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 3.5824. Min Range: -3.5824

Max Act: 3.4570. Min Act: -0.1700

Data Index: 1308221 (C4 (Web Text))

Max Activating Token Index: 324