Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.6766. Min Act: -0.1700
Data Index: 2609196 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.6141. Min Act: -0.1700
Data Index: 6582514 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.5516. Min Act: -0.1700
Data Index: 2563333 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.5203. Min Act: -0.1700
Data Index: 5633635 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.5203. Min Act: -0.1700
Data Index: 5936026 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.5203. Min Act: -0.1700
Data Index: 5171860 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.4266. Min Act: -0.1700
Data Index: 5781638 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.4266. Min Act: -0.1700
Data Index: 3667401 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.4578. Min Act: -0.1700
Data Index: 633752 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.3953. Min Act: -0.1700
Data Index: 5243884 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.3641. Min Act: -0.1700
Data Index: 1718511 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.3641. Min Act: -0.1700
Data Index: 5243883 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.3953. Min Act: -0.1700
Data Index: 3234699 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.3641. Min Act: -0.1700
Data Index: 7615412 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.3641. Min Act: -0.1700
Data Index: 636005 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.3641. Min Act: -0.1700
Data Index: 2684223 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.3641. Min Act: -0.1700
Data Index: 5075070 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.3016. Min Act: -0.1700
Data Index: 1917991 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.3641. Min Act: -0.1700
Data Index: 3436629 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6766. Min Range: -5.6766
Max Act: 5.3016. Min Act: -0.1700
Data Index: 7463922 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19