Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 577 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1267. Min Range: -8.1267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 2701554 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1267. Min Range: -8.1267
Max Act: 8.0642. Min Act: -0.1700
Data Index: 571546 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1267. Min Range: -8.1267
Max Act: 8.0017. Min Act: -0.1700
Data Index: 5857890 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1267. Min Range: -8.1267
Max Act: 8.0017. Min Act: -0.1700
Data Index: 2298906 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.8142. Min Act: -0.1700
Data Index: 7868694 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.7517. Min Act: -0.1700
Data Index: 2735575 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.7517. Min Act: -0.1700
Data Index: 757039 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.7517. Min Act: -0.1700
Data Index: 4603153 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.6892. Min Act: -0.1700
Data Index: 3804619 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.6892. Min Act: -0.1700
Data Index: 2932563 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.6579. Min Act: -0.1700
Data Index: 6762198 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.6579. Min Act: -0.1700
Data Index: 2690880 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.6267. Min Act: -0.1700
Data Index: 5804200 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.6267. Min Act: -0.1700
Data Index: 8291753 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.5642. Min Act: -0.1700
Data Index: 5739003 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.5642. Min Act: -0.1700
Data Index: 7851355 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.5642. Min Act: -0.1700
Data Index: 6976902 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.5642. Min Act: -0.1700
Data Index: 8802063 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.5329. Min Act: -0.1700
Data Index: 8119850 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1267. Min Range: -8.1267
Max Act: 7.5329. Min Act: -0.1700
Data Index: 5864766 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19