Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1048. Min Range: -4.1048
Max Act: 4.1048. Min Act: -0.1700
Data Index: 4769906 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1048. Min Range: -4.1048
Max Act: 4.1048. Min Act: -0.1700
Data Index: 7404294 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1048. Min Range: -4.1048
Max Act: 4.0736. Min Act: -0.1700
Data Index: 6988736 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1048. Min Range: -4.1048
Max Act: 4.0111. Min Act: -0.1700
Data Index: 7033819 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1048. Min Range: -4.1048
Max Act: 4.0111. Min Act: -0.1700
Data Index: 1709598 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1048. Min Range: -4.1048
Max Act: 4.0111. Min Act: -0.1700
Data Index: 5111532 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9798. Min Act: -0.1700
Data Index: 8120479 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9798. Min Act: -0.1700
Data Index: 1189626 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9798. Min Act: -0.1700
Data Index: 799426 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9798. Min Act: -0.1700
Data Index: 8166380 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9798. Min Act: -0.1700
Data Index: 72355 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9798. Min Act: -0.1700
Data Index: 6907503 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9485. Min Act: -0.1700
Data Index: 6923185 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9798. Min Act: -0.1700
Data Index: 2856537 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9173. Min Act: -0.1700
Data Index: 6127223 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9485. Min Act: -0.1700
Data Index: 6898039 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9173. Min Act: -0.1700
Data Index: 1130170 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9173. Min Act: -0.1700
Data Index: 4759203 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9173. Min Act: -0.1700
Data Index: 5346005 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1048. Min Range: -4.1048
Max Act: 3.9173. Min Act: -0.1700
Data Index: 4144821 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19