Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2712 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.6601. Min Act: -0.1700
Data Index: 8746067 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.5038. Min Act: -0.1700
Data Index: 8751342 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.4726. Min Act: -0.1700
Data Index: 3050818 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.4413. Min Act: -0.1700
Data Index: 6806836 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.4413. Min Act: -0.1700
Data Index: 1265616 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.4101. Min Act: -0.1700
Data Index: 1674743 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.3163. Min Act: -0.1700
Data Index: 3050823 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.3163. Min Act: -0.1700
Data Index: 1232962 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.3163. Min Act: -0.1700
Data Index: 64743 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.3163. Min Act: -0.1700
Data Index: 6102805 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.2851. Min Act: -0.1700
Data Index: 6710025 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.2851. Min Act: -0.1700
Data Index: 986255 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.2538. Min Act: -0.1700
Data Index: 6686918 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.2226. Min Act: -0.1700
Data Index: 288128 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.2226. Min Act: -0.1700
Data Index: 3360945 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.1913. Min Act: -0.1700
Data Index: 3327636 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.1601. Min Act: -0.1700
Data Index: 7282876 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.1601. Min Act: -0.1700
Data Index: 3489211 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.0976. Min Act: -0.1700
Data Index: 2952127 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.0976. Min Act: -0.1700
Data Index: 8225107 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19