Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2211. Min Range: -4.2211
Max Act: 4.2211. Min Act: -0.1700
Data Index: 195120 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2211. Min Range: -4.2211
Max Act: 4.0024. Min Act: -0.1700
Data Index: 7321961 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.9711. Min Act: -0.1700
Data Index: 7084550 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.9711. Min Act: -0.1700
Data Index: 7171500 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.8773. Min Act: -0.1700
Data Index: 6769660 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.8773. Min Act: -0.1700
Data Index: 8529330 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.8773. Min Act: -0.1700
Data Index: 5217649 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.8773. Min Act: -0.1700
Data Index: 6406942 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.8460. Min Act: -0.1700
Data Index: 7903387 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.8460. Min Act: -0.1700
Data Index: 3009816 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.8460. Min Act: -0.1700
Data Index: 2015211 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.8460. Min Act: -0.1700
Data Index: 1977740 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.8148. Min Act: -0.1700
Data Index: 7554110 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.8148. Min Act: -0.1700
Data Index: 1431394 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.8148. Min Act: -0.1700
Data Index: 5452395 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.7835. Min Act: -0.1700
Data Index: 6619636 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.7835. Min Act: -0.1700
Data Index: 6341114 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.7835. Min Act: -0.1700
Data Index: 2258465 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.7835. Min Act: -0.1700
Data Index: 3985299 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2211. Min Range: -4.2211
Max Act: 3.7835. Min Act: -0.1700
Data Index: 7728226 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19