Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.6762. Min Act: -0.1700
Data Index: 8739379 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.6762. Min Act: -0.1700
Data Index: 1960882 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.6449. Min Act: -0.1700
Data Index: 5415451 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.6449. Min Act: -0.1700
Data Index: 112406 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.4887. Min Act: -0.1700
Data Index: 4290741 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.4887. Min Act: -0.1700
Data Index: 1737829 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.4574. Min Act: -0.1700
Data Index: 4161791 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.4574. Min Act: -0.1700
Data Index: 7058856 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.4574. Min Act: -0.1700
Data Index: 2513175 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.4262. Min Act: -0.1700
Data Index: 203783 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.3949. Min Act: -0.1700
Data Index: 3463853 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.3949. Min Act: -0.1700
Data Index: 8552700 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.4262. Min Act: -0.1700
Data Index: 8624240 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.3637. Min Act: -0.1700
Data Index: 4405404 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.3949. Min Act: -0.1700
Data Index: 6898658 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.3637. Min Act: -0.1700
Data Index: 7411870 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.3637. Min Act: -0.1700
Data Index: 4548995 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.3324. Min Act: -0.1700
Data Index: 870402 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.3324. Min Act: -0.1700
Data Index: 7857365 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6762. Min Range: -6.6762
Max Act: 6.3324. Min Act: -0.1700
Data Index: 5000373 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19