Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3347 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.5229. Min Act: -0.1700
Data Index: 2942244 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.4604. Min Act: -0.1700
Data Index: 975021 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.4604. Min Act: -0.1700
Data Index: 7704716 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.3979. Min Act: -0.1700
Data Index: 8612343 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.4291. Min Act: -0.1700
Data Index: 8504815 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.3666. Min Act: -0.1700
Data Index: 2307829 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.3666. Min Act: -0.1700
Data Index: 5419687 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.3666. Min Act: -0.1700
Data Index: 1732 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.3666. Min Act: -0.1700
Data Index: 3877266 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.3354. Min Act: -0.1700
Data Index: 3142278 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.3354. Min Act: -0.1700
Data Index: 7135975 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.3354. Min Act: -0.1700
Data Index: 7602783 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.2729. Min Act: -0.1700
Data Index: 3888123 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.2729. Min Act: -0.1700
Data Index: 2031375 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.2416. Min Act: -0.1700
Data Index: 6001258 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.2416. Min Act: -0.1700
Data Index: 2627566 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.2416. Min Act: -0.1700
Data Index: 6813742 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.2416. Min Act: -0.1700
Data Index: 5763950 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.2416. Min Act: -0.1700
Data Index: 759634 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5229. Min Range: -7.5229
Max Act: 7.2416. Min Act: -0.1700
Data Index: 8084118 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19