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

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

Neuron 532 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: 3.2901. Min Range: -3.2901

Max Act: 3.2901. Min Act: -0.1700

Data Index: 1023584 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.2272. Min Act: -0.1700

Data Index: 772724 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.2272. Min Act: -0.1700

Data Index: 1313355 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.2115. Min Act: -0.1700

Data Index: 220937 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1800. Min Act: -0.1700

Data Index: 1029732 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1643. Min Act: -0.1700

Data Index: 1307801 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1643. Min Act: -0.1700

Data Index: 424104 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1328. Min Act: -0.1700

Data Index: 609284 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1485. Min Act: -0.1700

Data Index: 1078555 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1328. Min Act: -0.1700

Data Index: 539290 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1012. Min Act: -0.1700

Data Index: 605916 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1328. Min Act: -0.1700

Data Index: 1274713 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1012. Min Act: -0.1700

Data Index: 1238398 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1170. Min Act: -0.1700

Data Index: 467151 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1012. Min Act: -0.1700

Data Index: 672921 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1170. Min Act: -0.1700

Data Index: 414717 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1170. Min Act: -0.1700

Data Index: 573417 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1170. Min Act: -0.1700

Data Index: 1053040 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.1012. Min Act: -0.1700

Data Index: 1141413 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 3.2901. Min Range: -3.2901

Max Act: 3.0855. Min Act: -0.1700

Data Index: 72379 (C4 (Web Text))

Max Activating Token Index: 519