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

Dataset: Open Web Text

Neuron 572 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: 3.9936. Min Range: -3.9936

Max Act: 3.9936. Min Act: -0.1700

Data Index: 8394062 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9564. Min Act: -0.1700

Data Index: 1347946 (Open Web Text)

Max Activating Token Index: 368

Text #2

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9532. Min Act: -0.1700

Data Index: 2845184 (Open Web Text)

Max Activating Token Index: 322

Text #3

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9447. Min Act: -0.1700

Data Index: 1048394 (Open Web Text)

Max Activating Token Index: 845

Text #4

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9430. Min Act: -0.1700

Data Index: 4804623 (Open Web Text)

Max Activating Token Index: 134

Text #5

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9515. Min Act: -0.1700

Data Index: 4701717 (Open Web Text)

Max Activating Token Index: 648

Text #6

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9275. Min Act: -0.1700

Data Index: 4551579 (Open Web Text)

Max Activating Token Index: 226

Text #7

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9250. Min Act: -0.1700

Data Index: 3993294 (Open Web Text)

Max Activating Token Index: 529

Text #8

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9047. Min Act: -0.1700

Data Index: 1066717 (Open Web Text)

Max Activating Token Index: 504

Text #9

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9020. Min Act: -0.1700

Data Index: 2507497 (Open Web Text)

Max Activating Token Index: 333

Text #10

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9133. Min Act: -0.1700

Data Index: 650931 (Open Web Text)

Max Activating Token Index: 920

Text #11

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9123. Min Act: -0.1700

Data Index: 996055 (Open Web Text)

Max Activating Token Index: 125

Text #12

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.9331. Min Act: -0.1700

Data Index: 3218017 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.8927. Min Act: -0.1700

Data Index: 5441563 (Open Web Text)

Max Activating Token Index: 750

Text #14

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.8971. Min Act: -0.1700

Data Index: 2875600 (Open Web Text)

Max Activating Token Index: 683

Text #15

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.8967. Min Act: -0.1700

Data Index: 822173 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.8639. Min Act: -0.1700

Data Index: 3492798 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.8891. Min Act: -0.1700

Data Index: 1453873 (Open Web Text)

Max Activating Token Index: 381

Text #18

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.8946. Min Act: -0.1700

Data Index: 3945687 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 3.9936. Min Range: -3.9936

Max Act: 3.8996. Min Act: -0.1700

Data Index: 1145457 (Open Web Text)

Max Activating Token Index: 510