Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2477 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2097. Min Range: -10.2097
Max Act: 10.2097. Min Act: -0.1700
Data Index: 1474876 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2097. Min Range: -10.2097
Max Act: 9.4597. Min Act: -0.1700
Data Index: 4346405 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2097. Min Range: -10.2097
Max Act: 9.2722. Min Act: -0.1700
Data Index: 5232700 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2097. Min Range: -10.2097
Max Act: 9.2722. Min Act: -0.1700
Data Index: 2042952 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2097. Min Range: -10.2097
Max Act: 9.2722. Min Act: -0.1700
Data Index: 6996504 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2097. Min Range: -10.2097
Max Act: 9.2097. Min Act: -0.1700
Data Index: 6298055 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2097. Min Range: -10.2097
Max Act: 9.0847. Min Act: -0.1700
Data Index: 6809702 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2097. Min Range: -10.2097
Max Act: 9.1472. Min Act: -0.1700
Data Index: 1251324 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2097. Min Range: -10.2097
Max Act: 9.0847. Min Act: -0.1700
Data Index: 3637769 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2097. Min Range: -10.2097
Max Act: 9.0847. Min Act: -0.1700
Data Index: 1291916 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2097. Min Range: -10.2097
Max Act: 9.0222. Min Act: -0.1700
Data Index: 4993428 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2097. Min Range: -10.2097
Max Act: 9.0222. Min Act: -0.1700
Data Index: 4848955 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2097. Min Range: -10.2097
Max Act: 8.9597. Min Act: -0.1700
Data Index: 1925935 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2097. Min Range: -10.2097
Max Act: 8.9597. Min Act: -0.1700
Data Index: 8667285 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2097. Min Range: -10.2097
Max Act: 8.9597. Min Act: -0.1700
Data Index: 4033607 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2097. Min Range: -10.2097
Max Act: 8.9597. Min Act: -0.1700
Data Index: 1199567 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2097. Min Range: -10.2097
Max Act: 8.8972. Min Act: -0.1700
Data Index: 3200899 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2097. Min Range: -10.2097
Max Act: 8.8347. Min Act: -0.1700
Data Index: 3411562 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2097. Min Range: -10.2097
Max Act: 8.8347. Min Act: -0.1700
Data Index: 6635821 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2097. Min Range: -10.2097
Max Act: 8.8347. Min Act: -0.1700
Data Index: 1248219 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19