Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1851. Min Range: -5.1851
Max Act: 5.1851. Min Act: -0.1700
Data Index: 3062064 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1851. Min Range: -5.1851
Max Act: 5.1539. Min Act: -0.1700
Data Index: 6408523 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1851. Min Range: -5.1851
Max Act: 5.1539. Min Act: -0.1700
Data Index: 2433672 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1851. Min Range: -5.1851
Max Act: 5.0914. Min Act: -0.1700
Data Index: 5491925 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1851. Min Range: -5.1851
Max Act: 5.0601. Min Act: -0.1700
Data Index: 1605194 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1851. Min Range: -5.1851
Max Act: 5.0289. Min Act: -0.1700
Data Index: 3546231 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.9976. Min Act: -0.1700
Data Index: 7671588 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.9351. Min Act: -0.1700
Data Index: 3047986 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.9351. Min Act: -0.1700
Data Index: 5622382 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.9351. Min Act: -0.1700
Data Index: 2370669 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.9039. Min Act: -0.1700
Data Index: 8343344 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.9039. Min Act: -0.1700
Data Index: 2002213 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.8726. Min Act: -0.1700
Data Index: 7532809 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.8726. Min Act: -0.1700
Data Index: 23607 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.8726. Min Act: -0.1700
Data Index: 5146873 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.8726. Min Act: -0.1700
Data Index: 686173 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.8414. Min Act: -0.1700
Data Index: 1887376 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.8726. Min Act: -0.1700
Data Index: 1903932 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.8101. Min Act: -0.1700
Data Index: 3241564 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1851. Min Range: -5.1851
Max Act: 4.8414. Min Act: -0.1700
Data Index: 4318992 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19