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

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

Neuron 529 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: 3.1306. Min Range: -3.1306

Max Act: 3.1306. Min Act: -0.1700

Data Index: 956055 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0991. Min Act: -0.1700

Data Index: 905170 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0833. Min Act: -0.1700

Data Index: 1211682 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.1149. Min Act: -0.1700

Data Index: 764825 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0675. Min Act: -0.1700

Data Index: 891439 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0044. Min Act: -0.1700

Data Index: 195644 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0360. Min Act: -0.1700

Data Index: 824429 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 3.1306. Min Range: -3.1306

Max Act: 2.9727. Min Act: -0.1700

Data Index: 1199965 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 3.1306. Min Range: -3.1306

Max Act: 2.9886. Min Act: -0.1700

Data Index: 589373 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0202. Min Act: -0.1700

Data Index: 967833 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.1306. Min Range: -3.1306

Max Act: 2.9886. Min Act: -0.1700

Data Index: 243492 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 3.1306. Min Range: -3.1306

Max Act: 2.9727. Min Act: -0.1700

Data Index: 1213183 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0202. Min Act: -0.1700

Data Index: 238073 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 3.1306. Min Range: -3.1306

Max Act: 2.9727. Min Act: -0.1700

Data Index: 1328157 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0044. Min Act: -0.1700

Data Index: 1303787 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0044. Min Act: -0.1700

Data Index: 798906 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 3.1306. Min Range: -3.1306

Max Act: 2.9886. Min Act: -0.1700

Data Index: 768616 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.1306. Min Range: -3.1306

Max Act: 2.9569. Min Act: -0.1700

Data Index: 708151 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 3.1306. Min Range: -3.1306

Max Act: 2.9411. Min Act: -0.1700

Data Index: 682378 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 3.1306. Min Range: -3.1306

Max Act: 2.9569. Min Act: -0.1700

Data Index: 115025 (C4 (Web Text))

Max Activating Token Index: 650