Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1149 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.7616. Min Act: -0.1700
Data Index: 4022782 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.6366. Min Act: -0.1700
Data Index: 777183 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.5741. Min Act: -0.1700
Data Index: 2290329 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.4491. Min Act: -0.1700
Data Index: 8615548 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.4491. Min Act: -0.1700
Data Index: 4311485 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.3241. Min Act: -0.1700
Data Index: 8218770 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.1991. Min Act: -0.1700
Data Index: 2091505 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.1991. Min Act: -0.1700
Data Index: 2935335 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.1991. Min Act: -0.1700
Data Index: 8689692 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.1991. Min Act: -0.1700
Data Index: 949805 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.1991. Min Act: -0.1700
Data Index: 5542552 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.0741. Min Act: -0.1700
Data Index: 8555568 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.0741. Min Act: -0.1700
Data Index: 3564771 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.0741. Min Act: -0.1700
Data Index: 5558269 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.0116. Min Act: -0.1700
Data Index: 5205383 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.0741. Min Act: -0.1700
Data Index: 8759937 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.0741. Min Act: -0.1700
Data Index: 8527384 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.0741. Min Act: -0.1700
Data Index: 1333504 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.0116. Min Act: -0.1700
Data Index: 6114764 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7616. Min Range: -9.7616
Max Act: 9.0116. Min Act: -0.1700
Data Index: 6272794 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19