Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4910 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0030. Min Range: -6.0030
Max Act: 6.0030. Min Act: -0.1700
Data Index: 2111204 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.9717. Min Act: -0.1700
Data Index: 5795327 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.9717. Min Act: -0.1700
Data Index: 890241 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.9717. Min Act: -0.1700
Data Index: 1564233 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.9092. Min Act: -0.1700
Data Index: 4900059 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.9092. Min Act: -0.1700
Data Index: 3944267 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8780. Min Act: -0.1700
Data Index: 2433656 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8780. Min Act: -0.1700
Data Index: 5952666 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8780. Min Act: -0.1700
Data Index: 1142952 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8467. Min Act: -0.1700
Data Index: 5300087 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8467. Min Act: -0.1700
Data Index: 7895365 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8155. Min Act: -0.1700
Data Index: 1945862 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8155. Min Act: -0.1700
Data Index: 1986535 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8155. Min Act: -0.1700
Data Index: 5787047 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8155. Min Act: -0.1700
Data Index: 7179470 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8155. Min Act: -0.1700
Data Index: 4932024 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8155. Min Act: -0.1700
Data Index: 881449 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.7842. Min Act: -0.1700
Data Index: 1838418 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.8155. Min Act: -0.1700
Data Index: 3543810 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0030. Min Range: -6.0030
Max Act: 5.7530. Min Act: -0.1700
Data Index: 6936560 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19