Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1995. Min Range: -7.1995
Max Act: 7.1995. Min Act: -0.1700
Data Index: 7456295 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1995. Min Range: -7.1995
Max Act: 7.1683. Min Act: -0.1700
Data Index: 3934737 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1995. Min Range: -7.1995
Max Act: 7.0433. Min Act: -0.1700
Data Index: 1117046 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1995. Min Range: -7.1995
Max Act: 7.1058. Min Act: -0.1700
Data Index: 935439 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1995. Min Range: -7.1995
Max Act: 7.0745. Min Act: -0.1700
Data Index: 8121402 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1995. Min Range: -7.1995
Max Act: 7.0745. Min Act: -0.1700
Data Index: 7533793 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1995. Min Range: -7.1995
Max Act: 7.0433. Min Act: -0.1700
Data Index: 6753119 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1995. Min Range: -7.1995
Max Act: 7.0120. Min Act: -0.1700
Data Index: 4821854 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1995. Min Range: -7.1995
Max Act: 7.0433. Min Act: -0.1700
Data Index: 4915774 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1995. Min Range: -7.1995
Max Act: 6.9808. Min Act: -0.1700
Data Index: 4495031 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1995. Min Range: -7.1995
Max Act: 6.9808. Min Act: -0.1700
Data Index: 5499266 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1995. Min Range: -7.1995
Max Act: 6.9495. Min Act: -0.1700
Data Index: 3054477 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1995. Min Range: -7.1995
Max Act: 6.9495. Min Act: -0.1700
Data Index: 4194267 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1995. Min Range: -7.1995
Max Act: 6.9183. Min Act: -0.1700
Data Index: 6661381 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1995. Min Range: -7.1995
Max Act: 6.8558. Min Act: -0.1700
Data Index: 2976885 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1995. Min Range: -7.1995
Max Act: 6.8245. Min Act: -0.1700
Data Index: 4262674 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1995. Min Range: -7.1995
Max Act: 6.8245. Min Act: -0.1700
Data Index: 2398634 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1995. Min Range: -7.1995
Max Act: 6.7933. Min Act: -0.1700
Data Index: 2051666 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1995. Min Range: -7.1995
Max Act: 6.7933. Min Act: -0.1700
Data Index: 2746623 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1995. Min Range: -7.1995
Max Act: 6.7933. Min Act: -0.1700
Data Index: 430248 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19