Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4534 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5648. Min Range: -8.5648
Max Act: 8.5648. Min Act: -0.1700
Data Index: 2731934 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5648. Min Range: -8.5648
Max Act: 8.4398. Min Act: -0.1700
Data Index: 2795382 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5648. Min Range: -8.5648
Max Act: 8.1898. Min Act: -0.1700
Data Index: 7217090 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5648. Min Range: -8.5648
Max Act: 8.1898. Min Act: -0.1700
Data Index: 8222453 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5648. Min Range: -8.5648
Max Act: 8.1898. Min Act: -0.1700
Data Index: 5782296 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5648. Min Range: -8.5648
Max Act: 8.1273. Min Act: -0.1700
Data Index: 2773846 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5648. Min Range: -8.5648
Max Act: 8.0648. Min Act: -0.1700
Data Index: 1620709 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5648. Min Range: -8.5648
Max Act: 8.0648. Min Act: -0.1700
Data Index: 367565 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5648. Min Range: -8.5648
Max Act: 8.0648. Min Act: -0.1700
Data Index: 5727178 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5648. Min Range: -8.5648
Max Act: 8.0023. Min Act: -0.1700
Data Index: 152321 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5648. Min Range: -8.5648
Max Act: 8.0023. Min Act: -0.1700
Data Index: 8363114 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5648. Min Range: -8.5648
Max Act: 7.9398. Min Act: -0.1700
Data Index: 8775736 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5648. Min Range: -8.5648
Max Act: 7.8773. Min Act: -0.1700
Data Index: 1231150 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5648. Min Range: -8.5648
Max Act: 7.9398. Min Act: -0.1700
Data Index: 5480979 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5648. Min Range: -8.5648
Max Act: 7.9398. Min Act: -0.1700
Data Index: 4601769 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5648. Min Range: -8.5648
Max Act: 7.8773. Min Act: -0.1700
Data Index: 465747 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5648. Min Range: -8.5648
Max Act: 7.8773. Min Act: -0.1700
Data Index: 4959418 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5648. Min Range: -8.5648
Max Act: 7.8773. Min Act: -0.1700
Data Index: 6074861 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5648. Min Range: -8.5648
Max Act: 7.8773. Min Act: -0.1700
Data Index: 2721386 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5648. Min Range: -8.5648
Max Act: 7.8773. Min Act: -0.1700
Data Index: 8526047 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19