Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6384 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3035. Min Range: -6.3035
Max Act: 6.3035. Min Act: -0.1700
Data Index: 1921673 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3035. Min Range: -6.3035
Max Act: 6.2410. Min Act: -0.1700
Data Index: 4116110 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3035. Min Range: -6.3035
Max Act: 6.1160. Min Act: -0.1700
Data Index: 3916208 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3035. Min Range: -6.3035
Max Act: 6.0535. Min Act: -0.1700
Data Index: 7051174 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3035. Min Range: -6.3035
Max Act: 6.0535. Min Act: -0.1700
Data Index: 3612568 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.9910. Min Act: -0.1700
Data Index: 4095447 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.9910. Min Act: -0.1700
Data Index: 3826508 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.9598. Min Act: -0.1700
Data Index: 7648825 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.9598. Min Act: -0.1700
Data Index: 7245881 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.9285. Min Act: -0.1700
Data Index: 8782509 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.9285. Min Act: -0.1700
Data Index: 5817601 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8973. Min Act: -0.1700
Data Index: 5214802 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8660. Min Act: -0.1700
Data Index: 2271738 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8973. Min Act: -0.1700
Data Index: 5698578 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8348. Min Act: -0.1700
Data Index: 1169294 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8348. Min Act: -0.1700
Data Index: 5876672 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8348. Min Act: -0.1700
Data Index: 5338220 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8348. Min Act: -0.1700
Data Index: 641557 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8348. Min Act: -0.1700
Data Index: 4823621 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3035. Min Range: -6.3035
Max Act: 5.8035. Min Act: -0.1700
Data Index: 465245 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19