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

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

Neuron 119 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: 4.0831. Min Range: -4.0831

Max Act: 4.0831. Min Act: -0.1700

Data Index: 953803 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 4.0831. Min Range: -4.0831

Max Act: 4.0206. Min Act: -0.1700

Data Index: 146384 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.9893. Min Act: -0.1700

Data Index: 1207793 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.9893. Min Act: -0.1700

Data Index: 1179758 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.9581. Min Act: -0.1700

Data Index: 1238132 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8330. Min Act: -0.1700

Data Index: 253955 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8642. Min Act: -0.1700

Data Index: 1130059 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8955. Min Act: -0.1700

Data Index: 118091 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8642. Min Act: -0.1700

Data Index: 127148 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8642. Min Act: -0.1700

Data Index: 875014 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8955. Min Act: -0.1699

Data Index: 1200200 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8955. Min Act: -0.1700

Data Index: 170977 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8955. Min Act: -0.1700

Data Index: 62271 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8642. Min Act: -0.1700

Data Index: 987951 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8642. Min Act: -0.1700

Data Index: 801128 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8642. Min Act: -0.1700

Data Index: 700348 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8330. Min Act: -0.1700

Data Index: 1303355 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8330. Min Act: -0.1700

Data Index: 1358182 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.8330. Min Act: -0.1700

Data Index: 789564 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 4.0831. Min Range: -4.0831

Max Act: 3.7704. Min Act: -0.1700

Data Index: 179593 (C4 (Web Text))

Max Activating Token Index: 751