Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4650 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.6311. Min Range: -10.6311
Max Act: 10.6311. Min Act: -0.1700
Data Index: 35014 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6311. Min Range: -10.6311
Max Act: 10.2561. Min Act: -0.1700
Data Index: 3475305 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6311. Min Range: -10.6311
Max Act: 10.1311. Min Act: -0.1700
Data Index: 4091287 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6311. Min Range: -10.6311
Max Act: 10.1311. Min Act: -0.1700
Data Index: 5173416 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6311. Min Range: -10.6311
Max Act: 10.0061. Min Act: -0.1700
Data Index: 6547500 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6311. Min Range: -10.6311
Max Act: 10.0061. Min Act: -0.1700
Data Index: 3018601 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.9436. Min Act: -0.1700
Data Index: 945752 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.9436. Min Act: -0.1700
Data Index: 8410661 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.9436. Min Act: -0.1700
Data Index: 3150218 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.8811. Min Act: -0.1700
Data Index: 3641373 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.9436. Min Act: -0.1700
Data Index: 4779494 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.8811. Min Act: -0.1700
Data Index: 8645540 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.8811. Min Act: -0.1700
Data Index: 2471507 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.8186. Min Act: -0.1700
Data Index: 7250762 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.8186. Min Act: -0.1700
Data Index: 2684084 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.7561. Min Act: -0.1700
Data Index: 4235930 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.8186. Min Act: -0.1700
Data Index: 1705717 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.7561. Min Act: -0.1700
Data Index: 2553562 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.7561. Min Act: -0.1700
Data Index: 4726956 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6311. Min Range: -10.6311
Max Act: 9.6936. Min Act: -0.1700
Data Index: 1910006 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19