Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0032. Min Range: -4.0032
Max Act: 4.0032. Min Act: -0.1700
Data Index: 2104899 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.9094. Min Act: -0.1700
Data Index: 5397931 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.7843. Min Act: -0.1700
Data Index: 5871998 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.7217. Min Act: -0.1700
Data Index: 5872002 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.7217. Min Act: -0.1700
Data Index: 7130696 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.6592. Min Act: -0.1700
Data Index: 2961520 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.6122. Min Act: -0.1700
Data Index: 8605991 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.6279. Min Act: -0.1700
Data Index: 4875307 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.5809. Min Act: -0.1700
Data Index: 5872003 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.5809. Min Act: -0.1700
Data Index: 7782139 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.5966. Min Act: -0.1700
Data Index: 7398754 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.5496. Min Act: -0.1700
Data Index: 4142713 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.5496. Min Act: -0.1700
Data Index: 5872012 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.5339. Min Act: -0.1700
Data Index: 6621420 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.5183. Min Act: -0.1700
Data Index: 4142715 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.5339. Min Act: -0.1700
Data Index: 7351274 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.5339. Min Act: -0.1700
Data Index: 2761264 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.5496. Min Act: -0.1700
Data Index: 2415084 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.5183. Min Act: -0.1700
Data Index: 5053147 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0032. Min Range: -4.0032
Max Act: 3.4870. Min Act: -0.1700
Data Index: 4902285 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19