Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.8101. Min Act: -0.1700
Data Index: 8225785 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.7163. Min Act: -0.1700
Data Index: 7667249 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.5913. Min Act: -0.1700
Data Index: 6977348 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.5913. Min Act: -0.1700
Data Index: 7530483 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.5913. Min Act: -0.1700
Data Index: 1151710 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.5601. Min Act: -0.1700
Data Index: 305355 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.5288. Min Act: -0.1700
Data Index: 5375238 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4976. Min Act: -0.1700
Data Index: 1396710 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4976. Min Act: -0.1700
Data Index: 8541256 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4976. Min Act: -0.1700
Data Index: 388033 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4976. Min Act: -0.1700
Data Index: 6273253 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4663. Min Act: -0.1700
Data Index: 945669 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4663. Min Act: -0.1700
Data Index: 6427403 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4663. Min Act: -0.1700
Data Index: 4227735 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4663. Min Act: -0.1700
Data Index: 2895638 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4663. Min Act: -0.1700
Data Index: 2147896 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4351. Min Act: -0.1700
Data Index: 5128847 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4351. Min Act: -0.1700
Data Index: 5608070 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4038. Min Act: -0.1700
Data Index: 3639462 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8101. Min Range: -4.8101
Max Act: 4.4351. Min Act: -0.1700
Data Index: 6568331 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19