Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3330 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.7400. Min Act: -0.1700
Data Index: 508393 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.5525. Min Act: -0.1700
Data Index: 8785649 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.6150. Min Act: -0.1700
Data Index: 8140533 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.5525. Min Act: -0.1700
Data Index: 1449859 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.4275. Min Act: -0.1700
Data Index: 4435059 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.3963. Min Act: -0.1700
Data Index: 509418 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.3963. Min Act: -0.1700
Data Index: 3227362 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.3650. Min Act: -0.1700
Data Index: 6573939 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.3650. Min Act: -0.1700
Data Index: 3795763 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.3650. Min Act: -0.1700
Data Index: 1157199 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.3338. Min Act: -0.1700
Data Index: 2338870 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.3025. Min Act: -0.1700
Data Index: 5252258 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.2713. Min Act: -0.1700
Data Index: 1933961 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.2400. Min Act: -0.1700
Data Index: 6785435 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.2088. Min Act: -0.1700
Data Index: 1039103 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.2088. Min Act: -0.1700
Data Index: 4901575 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.2088. Min Act: -0.1700
Data Index: 6666435 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.1775. Min Act: -0.1700
Data Index: 226038 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.1775. Min Act: -0.1700
Data Index: 2511723 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7400. Min Range: -7.7400
Max Act: 7.1775. Min Act: -0.1700
Data Index: 6129448 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19