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

Dataset: Open Web Text

Neuron 525 in Layer 4

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: 3.6932. Min Range: -3.6932

Max Act: 3.6852. Min Act: -0.1700

Data Index: 2873393 (Open Web Text)

Max Activating Token Index: 896

Text #1

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6932. Min Act: -0.1700

Data Index: 8410924 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6499. Min Act: -0.1700

Data Index: 2585167 (Open Web Text)

Max Activating Token Index: 988

Text #3

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6669. Min Act: -0.1700

Data Index: 1573758 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6681. Min Act: -0.1700

Data Index: 6093185 (Open Web Text)

Max Activating Token Index: 118

Text #5

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5998. Min Act: -0.1700

Data Index: 3871356 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6461. Min Act: -0.1700

Data Index: 1119432 (Open Web Text)

Max Activating Token Index: 411

Text #7

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.6015. Min Act: -0.1700

Data Index: 5517015 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5945. Min Act: -0.1700

Data Index: 3346719 (Open Web Text)

Max Activating Token Index: 855

Text #9

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5921. Min Act: -0.1700

Data Index: 4835777 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5780. Min Act: -0.1700

Data Index: 4496923 (Open Web Text)

Max Activating Token Index: 787

Text #11

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5750. Min Act: -0.1700

Data Index: 6935777 (Open Web Text)

Max Activating Token Index: 889

Text #12

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5767. Min Act: -0.1700

Data Index: 3817919 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5550. Min Act: -0.1700

Data Index: 8723517 (Open Web Text)

Max Activating Token Index: 880

Text #14

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5639. Min Act: -0.1700

Data Index: 4188478 (Open Web Text)

Max Activating Token Index: 172

Text #15

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5809. Min Act: -0.1700

Data Index: 5607860 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5696. Min Act: -0.1700

Data Index: 5906846 (Open Web Text)

Max Activating Token Index: 844

Text #17

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5658. Min Act: -0.1700

Data Index: 6229507 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5635. Min Act: -0.1700

Data Index: 6718532 (Open Web Text)

Max Activating Token Index: 131

Text #19

Max Range: 3.6932. Min Range: -3.6932

Max Act: 3.5610. Min Act: -0.1700

Data Index: 1161193 (Open Web Text)

Max Activating Token Index: 5