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

Dataset: Open Web Text

Neuron 536 in Layer 0

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: 3.2735. Min Range: -3.2735

Max Act: 3.2735. Min Act: -0.1700

Data Index: 5420946 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1674. Min Act: -0.1700

Data Index: 4172420 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1514. Min Act: -0.1700

Data Index: 1654021 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1509. Min Act: -0.1700

Data Index: 6686686 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1441. Min Act: -0.1700

Data Index: 6997528 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1374. Min Act: -0.1700

Data Index: 1523867 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1358. Min Act: -0.1700

Data Index: 4068842 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1267. Min Act: -0.1700

Data Index: 3194542 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1156. Min Act: -0.1700

Data Index: 7071107 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.1246. Min Act: -0.1700

Data Index: 3985631 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0971. Min Act: -0.1700

Data Index: 5412976 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0940. Min Act: -0.1700

Data Index: 4711741 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0891. Min Act: -0.1700

Data Index: 4617069 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0971. Min Act: -0.1700

Data Index: 5929598 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0776. Min Act: -0.1700

Data Index: 1994154 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0766. Min Act: -0.1700

Data Index: 1707519 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0734. Min Act: -0.1700

Data Index: 8302138 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0782. Min Act: -0.1700

Data Index: 177747 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0791. Min Act: -0.1700

Data Index: 1795821 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.2735. Min Range: -3.2735

Max Act: 3.0782. Min Act: -0.1700

Data Index: 202424 (Open Web Text)

Max Activating Token Index: 4