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

Dataset: Open Web Text

Neuron 1165 in Layer 3

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: 3.3658. Min Range: -3.3658

Max Act: 3.3658. Min Act: -0.1700

Data Index: 7285687 (Open Web Text)

Max Activating Token Index: 653

Text #1

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.2221. Min Act: -0.1700

Data Index: 1183087 (Open Web Text)

Max Activating Token Index: 368

Text #2

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.2305. Min Act: -0.1700

Data Index: 3658214 (Open Web Text)

Max Activating Token Index: 348

Text #3

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.1944. Min Act: -0.1700

Data Index: 7875255 (Open Web Text)

Max Activating Token Index: 728

Text #4

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.1827. Min Act: -0.1699

Data Index: 7134450 (Open Web Text)

Max Activating Token Index: 688

Text #5

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.1256. Min Act: -0.1700

Data Index: 5778046 (Open Web Text)

Max Activating Token Index: 820

Text #6

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.1074. Min Act: -0.1700

Data Index: 7910150 (Open Web Text)

Max Activating Token Index: 548

Text #7

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.1270. Min Act: -0.1700

Data Index: 3880249 (Open Web Text)

Max Activating Token Index: 857

Text #8

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.0598. Min Act: -0.1700

Data Index: 2933261 (Open Web Text)

Max Activating Token Index: 156

Text #9

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.0284. Min Act: -0.1700

Data Index: 6163780 (Open Web Text)

Max Activating Token Index: 81

Text #10

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.0660. Min Act: -0.1700

Data Index: 7382242 (Open Web Text)

Max Activating Token Index: 757

Text #11

Max Range: 3.3658. Min Range: -3.3658

Max Act: 2.9769. Min Act: -0.1697

Data Index: 5117374 (Open Web Text)

Max Activating Token Index: 882

Text #12

Max Range: 3.3658. Min Range: -3.3658

Max Act: 2.9640. Min Act: -0.1700

Data Index: 8335187 (Open Web Text)

Max Activating Token Index: 625

Text #13

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.0087. Min Act: -0.1700

Data Index: 2012737 (Open Web Text)

Max Activating Token Index: 644

Text #14

Max Range: 3.3658. Min Range: -3.3658

Max Act: 2.9889. Min Act: -0.1697

Data Index: 7112515 (Open Web Text)

Max Activating Token Index: 536

Text #15

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.0231. Min Act: -0.1700

Data Index: 1215945 (Open Web Text)

Max Activating Token Index: 434

Text #16

Max Range: 3.3658. Min Range: -3.3658

Max Act: 3.0155. Min Act: -0.1695

Data Index: 8185805 (Open Web Text)

Max Activating Token Index: 129

Text #17

Max Range: 3.3658. Min Range: -3.3658

Max Act: 2.9754. Min Act: -0.1700

Data Index: 3689281 (Open Web Text)

Max Activating Token Index: 630

Text #18

Max Range: 3.3658. Min Range: -3.3658

Max Act: 2.9759. Min Act: -0.1698

Data Index: 5194186 (Open Web Text)

Max Activating Token Index: 307

Text #19

Max Range: 3.3658. Min Range: -3.3658

Max Act: 2.9618. Min Act: -0.1700

Data Index: 4720251 (Open Web Text)

Max Activating Token Index: 244