Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2780 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.1389. Min Act: -0.1700

Data Index: 5996680 (Open Web Text)

Max Activating Token Index: 564

Text #1

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.1149. Min Act: -0.1700

Data Index: 5002721 (Open Web Text)

Max Activating Token Index: 704

Text #2

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.1031. Min Act: -0.1700

Data Index: 5207132 (Open Web Text)

Max Activating Token Index: 920

Text #3

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.1122. Min Act: -0.1700

Data Index: 4571012 (Open Web Text)

Max Activating Token Index: 695

Text #4

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0744. Min Act: -0.1700

Data Index: 1734529 (Open Web Text)

Max Activating Token Index: 586

Text #5

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0038. Min Act: -0.1700

Data Index: 5367240 (Open Web Text)

Max Activating Token Index: 610

Text #6

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0594. Min Act: -0.1700

Data Index: 8343515 (Open Web Text)

Max Activating Token Index: 683

Text #7

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0431. Min Act: -0.1700

Data Index: 7844311 (Open Web Text)

Max Activating Token Index: 290

Text #8

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0070. Min Act: -0.1700

Data Index: 7918274 (Open Web Text)

Max Activating Token Index: 197

Text #9

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0199. Min Act: -0.1700

Data Index: 3721184 (Open Web Text)

Max Activating Token Index: 121

Text #10

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9652. Min Act: -0.1700

Data Index: 4531986 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0130. Min Act: -0.1700

Data Index: 2308202 (Open Web Text)

Max Activating Token Index: 618

Text #12

Max Range: 4.1389. Min Range: -4.1389

Max Act: 4.0231. Min Act: -0.1700

Data Index: 948614 (Open Web Text)

Max Activating Token Index: 631

Text #13

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9954. Min Act: -0.1700

Data Index: 2317984 (Open Web Text)

Max Activating Token Index: 812

Text #14

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9865. Min Act: -0.1700

Data Index: 6642132 (Open Web Text)

Max Activating Token Index: 874

Text #15

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9370. Min Act: -0.1700

Data Index: 808379 (Open Web Text)

Max Activating Token Index: 496

Text #16

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9909. Min Act: -0.1700

Data Index: 4669591 (Open Web Text)

Max Activating Token Index: 444

Text #17

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9608. Min Act: -0.1700

Data Index: 1847302 (Open Web Text)

Max Activating Token Index: 470

Text #18

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9348. Min Act: -0.1700

Data Index: 157437 (Open Web Text)

Max Activating Token Index: 736

Text #19

Max Range: 4.1389. Min Range: -4.1389

Max Act: 3.9722. Min Act: -0.1700

Data Index: 5395850 (Open Web Text)

Max Activating Token Index: 455