Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4231 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.8859. Min Act: -0.1700
Data Index: 5171637 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.7921. Min Act: -0.1700
Data Index: 6061542 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.7921. Min Act: -0.1700
Data Index: 6821155 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.7609. Min Act: -0.1700
Data Index: 343999 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.6984. Min Act: -0.1700
Data Index: 4552664 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.6359. Min Act: -0.1700
Data Index: 2153711 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.6046. Min Act: -0.1700
Data Index: 3387342 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.6046. Min Act: -0.1700
Data Index: 823233 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.6046. Min Act: -0.1700
Data Index: 4324083 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.6046. Min Act: -0.1700
Data Index: 3767093 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.5734. Min Act: -0.1700
Data Index: 3825261 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.5109. Min Act: -0.1700
Data Index: 1669920 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.4171. Min Act: -0.1700
Data Index: 414351 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.3859. Min Act: -0.1700
Data Index: 3374848 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.3859. Min Act: -0.1700
Data Index: 6529187 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.3546. Min Act: -0.1700
Data Index: 4874312 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.3546. Min Act: -0.1700
Data Index: 8365365 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.3234. Min Act: -0.1700
Data Index: 4873752 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.3234. Min Act: -0.1700
Data Index: 4466022 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8859. Min Range: -6.8859
Max Act: 6.2921. Min Act: -0.1700
Data Index: 9375 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19