Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1569 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.7928. Min Act: -0.1700

Data Index: 638276 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.6990. Min Act: -0.1700

Data Index: 167793 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.7303. Min Act: -0.1700

Data Index: 150719 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.7303. Min Act: -0.1700

Data Index: 1350062 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.6678. Min Act: -0.1700

Data Index: 419734 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.6990. Min Act: -0.1700

Data Index: 1355508 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.6365. Min Act: -0.1700

Data Index: 189305 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.6678. Min Act: -0.1700

Data Index: 381018 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.5740. Min Act: -0.1700

Data Index: 883501 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.6365. Min Act: -0.1700

Data Index: 439831 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.4959. Min Act: -0.1700

Data Index: 855821 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.4959. Min Act: -0.1700

Data Index: 991644 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.5115. Min Act: -0.1700

Data Index: 300206 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.5428. Min Act: -0.1700

Data Index: 1095900 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.5428. Min Act: -0.1700

Data Index: 557031 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.5740. Min Act: -0.1700

Data Index: 375391 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.5428. Min Act: -0.1700

Data Index: 1197581 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.5428. Min Act: -0.1700

Data Index: 917717 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.4803. Min Act: -0.1700

Data Index: 871618 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 5.7928. Min Range: -5.7928

Max Act: 5.4647. Min Act: -0.1700

Data Index: 681164 (C4 (Web Text))

Max Activating Token Index: 830