Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.6311. Min Act: -0.1700
Data Index: 1680382 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.5686. Min Act: -0.1700
Data Index: 7045980 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.5061. Min Act: -0.1700
Data Index: 6300745 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.4436. Min Act: -0.1700
Data Index: 5618391 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.3811. Min Act: -0.1700
Data Index: 4085477 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.3811. Min Act: -0.1700
Data Index: 5440716 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.3811. Min Act: -0.1700
Data Index: 5195313 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.3186. Min Act: -0.1700
Data Index: 8204802 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.2561. Min Act: -0.1700
Data Index: 1255813 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.2561. Min Act: -0.1700
Data Index: 8810715 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.2561. Min Act: -0.1700
Data Index: 7103572 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.1936. Min Act: -0.1700
Data Index: 2829990 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.1936. Min Act: -0.1700
Data Index: 3930833 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.0686. Min Act: -0.1700
Data Index: 2887197 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.0686. Min Act: -0.1700
Data Index: 1232048 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.0686. Min Act: -0.1700
Data Index: 8527461 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.0061. Min Act: -0.1700
Data Index: 4876998 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.0061. Min Act: -0.1700
Data Index: 357625 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.0061. Min Act: -0.1700
Data Index: 3234089 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6311. Min Range: -8.6311
Max Act: 8.0061. Min Act: -0.1700
Data Index: 1948703 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19