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

Dataset: Open Web Text

Neuron 2806 in Layer 5

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: 4.2582. Min Range: -4.2582

Max Act: 4.2582. Min Act: -0.1700

Data Index: 8044629 (Open Web Text)

Max Activating Token Index: 335

Text #1

Max Range: 4.2582. Min Range: -4.2582

Max Act: 4.1521. Min Act: -0.1700

Data Index: 6370265 (Open Web Text)

Max Activating Token Index: 179

Text #2

Max Range: 4.2582. Min Range: -4.2582

Max Act: 4.0986. Min Act: -0.1700

Data Index: 8603827 (Open Web Text)

Max Activating Token Index: 381

Text #3

Max Range: 4.2582. Min Range: -4.2582

Max Act: 4.1244. Min Act: -0.1700

Data Index: 2286737 (Open Web Text)

Max Activating Token Index: 714

Text #4

Max Range: 4.2582. Min Range: -4.2582

Max Act: 4.0732. Min Act: -0.1700

Data Index: 2926064 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 4.2582. Min Range: -4.2582

Max Act: 4.0929. Min Act: -0.1700

Data Index: 3875214 (Open Web Text)

Max Activating Token Index: 717

Text #6

Max Range: 4.2582. Min Range: -4.2582

Max Act: 4.0580. Min Act: -0.1700

Data Index: 7020586 (Open Web Text)

Max Activating Token Index: 867

Text #7

Max Range: 4.2582. Min Range: -4.2582

Max Act: 4.0408. Min Act: -0.1700

Data Index: 5953716 (Open Web Text)

Max Activating Token Index: 62

Text #8

Max Range: 4.2582. Min Range: -4.2582

Max Act: 3.9959. Min Act: -0.1700

Data Index: 6824710 (Open Web Text)

Max Activating Token Index: 654

Text #9

Max Range: 4.2582. Min Range: -4.2582

Max Act: 4.0285. Min Act: -0.1700

Data Index: 4341308 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 4.2582. Min Range: -4.2582

Max Act: 3.9829. Min Act: -0.1700

Data Index: 352082 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 4.2582. Min Range: -4.2582

Max Act: 4.0068. Min Act: -0.1700

Data Index: 4929860 (Open Web Text)

Max Activating Token Index: 317

Text #12

Max Range: 4.2582. Min Range: -4.2582

Max Act: 3.9514. Min Act: -0.1700

Data Index: 3016113 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 4.2582. Min Range: -4.2582

Max Act: 3.9926. Min Act: -0.1700

Data Index: 6797564 (Open Web Text)

Max Activating Token Index: 939

Text #14

Max Range: 4.2582. Min Range: -4.2582

Max Act: 3.9747. Min Act: -0.1700

Data Index: 4341309 (Open Web Text)

Max Activating Token Index: 44

Text #15

Max Range: 4.2582. Min Range: -4.2582

Max Act: 3.9249. Min Act: -0.1700

Data Index: 2245779 (Open Web Text)

Max Activating Token Index: 555

Text #16

Max Range: 4.2582. Min Range: -4.2582

Max Act: 3.9275. Min Act: -0.1700

Data Index: 3718791 (Open Web Text)

Max Activating Token Index: 347

Text #17

Max Range: 4.2582. Min Range: -4.2582

Max Act: 3.9578. Min Act: -0.1700

Data Index: 3956419 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 4.2582. Min Range: -4.2582

Max Act: 3.9128. Min Act: -0.1700

Data Index: 4473997 (Open Web Text)

Max Activating Token Index: 692

Text #19

Max Range: 4.2582. Min Range: -4.2582

Max Act: 3.8891. Min Act: -0.1700

Data Index: 3214010 (Open Web Text)

Max Activating Token Index: 470