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

Dataset: Open Web Text

Neuron 1327 in Layer 4

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: 3.8736. Min Range: -3.8736

Max Act: 3.8594. Min Act: -0.1700

Data Index: 1303324 (Open Web Text)

Max Activating Token Index: 925

Text #1

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.8569. Min Act: -0.1700

Data Index: 4926196 (Open Web Text)

Max Activating Token Index: 1018

Text #2

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.8736. Min Act: -0.1700

Data Index: 4425944 (Open Web Text)

Max Activating Token Index: 501

Text #3

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.8456. Min Act: -0.1700

Data Index: 7280323 (Open Web Text)

Max Activating Token Index: 976

Text #4

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.8095. Min Act: -0.1700

Data Index: 1318639 (Open Web Text)

Max Activating Token Index: 300

Text #5

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7949. Min Act: -0.1700

Data Index: 2288806 (Open Web Text)

Max Activating Token Index: 311

Text #6

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7986. Min Act: -0.1700

Data Index: 7517845 (Open Web Text)

Max Activating Token Index: 634

Text #7

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7188. Min Act: -0.1700

Data Index: 3102909 (Open Web Text)

Max Activating Token Index: 85

Text #8

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7453. Min Act: -0.1700

Data Index: 6914725 (Open Web Text)

Max Activating Token Index: 857

Text #9

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7282. Min Act: -0.1700

Data Index: 3584800 (Open Web Text)

Max Activating Token Index: 812

Text #10

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7142. Min Act: -0.1700

Data Index: 1893690 (Open Web Text)

Max Activating Token Index: 978

Text #11

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.6878. Min Act: -0.1700

Data Index: 241889 (Open Web Text)

Max Activating Token Index: 337

Text #12

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7197. Min Act: -0.1700

Data Index: 7733963 (Open Web Text)

Max Activating Token Index: 153

Text #13

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.6960. Min Act: -0.1700

Data Index: 4105189 (Open Web Text)

Max Activating Token Index: 953

Text #14

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.6953. Min Act: -0.1700

Data Index: 4479838 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7240. Min Act: -0.1700

Data Index: 7738347 (Open Web Text)

Max Activating Token Index: 530

Text #16

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7152. Min Act: -0.1700

Data Index: 8630541 (Open Web Text)

Max Activating Token Index: 171

Text #17

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7189. Min Act: -0.1700

Data Index: 5859276 (Open Web Text)

Max Activating Token Index: 305

Text #18

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.7115. Min Act: -0.1700

Data Index: 1567889 (Open Web Text)

Max Activating Token Index: 155

Text #19

Max Range: 3.8736. Min Range: -3.8736

Max Act: 3.6659. Min Act: -0.1700

Data Index: 6621124 (Open Web Text)

Max Activating Token Index: 562