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

Dataset: Open Web Text

Neuron 1538 in Layer 2

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: 1.9148. Min Range: -1.9148

Max Act: 1.9148. Min Act: -0.1698

Data Index: 3722178 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.9064. Min Act: -0.1700

Data Index: 2352315 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.9064. Min Act: -0.1699

Data Index: 8067084 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.8698. Min Act: -0.1700

Data Index: 875499 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.8177. Min Act: -0.1700

Data Index: 517149 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.8131. Min Act: -0.1699

Data Index: 4888904 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.8117. Min Act: -0.1700

Data Index: 5358045 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.8112. Min Act: -0.1700

Data Index: 269308 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7974. Min Act: -0.1699

Data Index: 6084843 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7974. Min Act: -0.1700

Data Index: 7763745 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7974. Min Act: -0.1699

Data Index: 3426435 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7745. Min Act: -0.1698

Data Index: 8650965 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7769. Min Act: -0.1695

Data Index: 2747810 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7508. Min Act: -0.1699

Data Index: 4653752 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7370. Min Act: -0.1699

Data Index: 1467384 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7285. Min Act: -0.1687

Data Index: 7342272 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7191. Min Act: -0.1697

Data Index: 979218 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7108. Min Act: -0.1700

Data Index: 2047725 (Open Web Text)

Max Activating Token Index: 507

Text #18

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.6981. Min Act: -0.1700

Data Index: 4172539 (Open Web Text)

Max Activating Token Index: 46

Text #19

Max Range: 1.9148. Min Range: -1.9148

Max Act: 1.7137. Min Act: -0.1700

Data Index: 2252670 (Open Web Text)

Max Activating Token Index: 3