Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2285. Min Range: -6.2285
Max Act: 6.2285. Min Act: -0.1700
Data Index: 1413160 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2285. Min Range: -6.2285
Max Act: 6.1972. Min Act: -0.1700
Data Index: 5670166 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2285. Min Range: -6.2285
Max Act: 6.1035. Min Act: -0.1700
Data Index: 3591188 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2285. Min Range: -6.2285
Max Act: 6.0722. Min Act: -0.1700
Data Index: 1408391 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2285. Min Range: -6.2285
Max Act: 6.0410. Min Act: -0.1700
Data Index: 2912432 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2285. Min Range: -6.2285
Max Act: 6.0097. Min Act: -0.1700
Data Index: 5070485 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.8847. Min Act: -0.1700
Data Index: 7477526 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.8535. Min Act: -0.1700
Data Index: 5088286 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.8535. Min Act: -0.1700
Data Index: 8696121 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.8535. Min Act: -0.1700
Data Index: 8057923 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.8535. Min Act: -0.1700
Data Index: 4321831 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.8222. Min Act: -0.1700
Data Index: 8379892 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.8222. Min Act: -0.1700
Data Index: 3039660 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.8222. Min Act: -0.1700
Data Index: 2496476 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.8222. Min Act: -0.1700
Data Index: 4014081 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.7910. Min Act: -0.1700
Data Index: 620946 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.7910. Min Act: -0.1700
Data Index: 6033585 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.7597. Min Act: -0.1700
Data Index: 1706912 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.7597. Min Act: -0.1700
Data Index: 3249831 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2285. Min Range: -6.2285
Max Act: 5.7597. Min Act: -0.1700
Data Index: 1697001 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19