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

Dataset: Open Web Text

Neuron 375 in Layer 6

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: 3.3681. Min Range: -3.3681

Max Act: 3.3681. Min Act: -0.1700

Data Index: 2922377 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.3053. Min Act: -0.1700

Data Index: 6875394 (Open Web Text)

Max Activating Token Index: 812

Text #2

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.3096. Min Act: -0.1700

Data Index: 1374010 (Open Web Text)

Max Activating Token Index: 762

Text #3

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.3086. Min Act: -0.1700

Data Index: 3207989 (Open Web Text)

Max Activating Token Index: 644

Text #4

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2135. Min Act: -0.1700

Data Index: 2921392 (Open Web Text)

Max Activating Token Index: 868

Text #5

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2244. Min Act: -0.1700

Data Index: 4957183 (Open Web Text)

Max Activating Token Index: 963

Text #6

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2086. Min Act: -0.1700

Data Index: 4569807 (Open Web Text)

Max Activating Token Index: 868

Text #7

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1610. Min Act: -0.1700

Data Index: 4107633 (Open Web Text)

Max Activating Token Index: 780

Text #8

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1821. Min Act: -0.1700

Data Index: 8538590 (Open Web Text)

Max Activating Token Index: 955

Text #9

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1373. Min Act: -0.1700

Data Index: 8730795 (Open Web Text)

Max Activating Token Index: 702

Text #10

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1148. Min Act: -0.1700

Data Index: 2922375 (Open Web Text)

Max Activating Token Index: 864

Text #11

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1149. Min Act: -0.1700

Data Index: 4959012 (Open Web Text)

Max Activating Token Index: 356

Text #12

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.0963. Min Act: -0.1700

Data Index: 6585412 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1003. Min Act: -0.1700

Data Index: 5503817 (Open Web Text)

Max Activating Token Index: 944

Text #14

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.0947. Min Act: -0.1700

Data Index: 5423806 (Open Web Text)

Max Activating Token Index: 601

Text #15

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.0981. Min Act: -0.1700

Data Index: 4994742 (Open Web Text)

Max Activating Token Index: 409

Text #16

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.0639. Min Act: -0.1700

Data Index: 431980 (Open Web Text)

Max Activating Token Index: 877

Text #17

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.0860. Min Act: -0.1700

Data Index: 3608413 (Open Web Text)

Max Activating Token Index: 811

Text #18

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.0805. Min Act: -0.1700

Data Index: 6722706 (Open Web Text)

Max Activating Token Index: 839

Text #19

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.0829. Min Act: -0.1700

Data Index: 2439705 (Open Web Text)

Max Activating Token Index: 889