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

Dataset: Open Web Text

Neuron 2992 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: 1.3284. Min Range: -1.3284

Max Act: 1.3284. Min Act: -0.1700

Data Index: 8030319 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.2225. Min Act: -0.1694

Data Index: 7066187 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.1734. Min Act: -0.1665

Data Index: 5133275 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.1455. Min Act: -0.1700

Data Index: 4326436 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.1264. Min Act: -0.1380

Data Index: 6696319 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0968. Min Act: -0.1698

Data Index: 4132525 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0978. Min Act: -0.1699

Data Index: 4815253 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0901. Min Act: -0.1700

Data Index: 7379991 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.1051. Min Act: -0.1681

Data Index: 5428834 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0888. Min Act: -0.1621

Data Index: 6667353 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0917. Min Act: -0.1692

Data Index: 928942 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0713. Min Act: -0.1700

Data Index: 1121685 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0698. Min Act: -0.1653

Data Index: 5822038 (Open Web Text)

Max Activating Token Index: 65

Text #13

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0726. Min Act: -0.1698

Data Index: 4189791 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0691. Min Act: -0.1653

Data Index: 5710821 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0616. Min Act: -0.1691

Data Index: 7967333 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0581. Min Act: -0.1663

Data Index: 8601951 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0540. Min Act: -0.1691

Data Index: 1332575 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0460. Min Act: -0.1700

Data Index: 6844506 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.3284. Min Range: -1.3284

Max Act: 1.0486. Min Act: -0.1699

Data Index: 208564 (Open Web Text)

Max Activating Token Index: 1023