Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 642 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.8731. Min Act: -0.1700
Data Index: 1661779 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.8418. Min Act: -0.1700
Data Index: 5252454 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.8418. Min Act: -0.1700
Data Index: 135246 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.8418. Min Act: -0.1700
Data Index: 7686944 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.8106. Min Act: -0.1700
Data Index: 6756894 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.8106. Min Act: -0.1700
Data Index: 5850514 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.7481. Min Act: -0.1700
Data Index: 5222862 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.7481. Min Act: -0.1700
Data Index: 5043031 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.7168. Min Act: -0.1700
Data Index: 5642698 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.7168. Min Act: -0.1700
Data Index: 3559254 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.6856. Min Act: -0.1700
Data Index: 5008754 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.6856. Min Act: -0.1700
Data Index: 8672727 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.6856. Min Act: -0.1700
Data Index: 6668433 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.6856. Min Act: -0.1700
Data Index: 7121531 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.6543. Min Act: -0.1700
Data Index: 8811211 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.5918. Min Act: -0.1700
Data Index: 8149154 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.6231. Min Act: -0.1700
Data Index: 380061 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.6231. Min Act: -0.1700
Data Index: 3562765 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.6231. Min Act: -0.1700
Data Index: 4675711 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8731. Min Range: -5.8731
Max Act: 5.6231. Min Act: -0.1700
Data Index: 6756893 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19