Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2828 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.7260. Min Act: -0.1700
Data Index: 7083820 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.3510. Min Act: -0.1700
Data Index: 3261930 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.3510. Min Act: -0.1700
Data Index: 1854488 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.2885. Min Act: -0.1700
Data Index: 3358686 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.2885. Min Act: -0.1700
Data Index: 5392892 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.2573. Min Act: -0.1700
Data Index: 1272157 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.2260. Min Act: -0.1700
Data Index: 8475045 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.1635. Min Act: -0.1700
Data Index: 5119009 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.1635. Min Act: -0.1700
Data Index: 7296501 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.1635. Min Act: -0.1700
Data Index: 7083819 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.1635. Min Act: -0.1700
Data Index: 8351553 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.1323. Min Act: -0.1700
Data Index: 869780 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.1323. Min Act: -0.1700
Data Index: 6252275 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.1323. Min Act: -0.1700
Data Index: 6184787 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.1010. Min Act: -0.1700
Data Index: 2275370 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.0698. Min Act: -0.1700
Data Index: 2030570 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.1010. Min Act: -0.1700
Data Index: 5932204 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.0698. Min Act: -0.1700
Data Index: 2388175 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.0698. Min Act: -0.1700
Data Index: 5290333 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7260. Min Range: -5.7260
Max Act: 5.0385. Min Act: -0.1700
Data Index: 7224356 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19