Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1639 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3452. Min Range: -8.3452
Max Act: 8.3452. Min Act: -0.1700
Data Index: 694385 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.9390. Min Act: -0.1700
Data Index: 6718351 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.8765. Min Act: -0.1700
Data Index: 7152733 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.8765. Min Act: -0.1700
Data Index: 4556868 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.8140. Min Act: -0.1700
Data Index: 7021926 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.7827. Min Act: -0.1700
Data Index: 8825155 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.6577. Min Act: -0.1700
Data Index: 5013356 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.6577. Min Act: -0.1700
Data Index: 688067 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.6265. Min Act: -0.1700
Data Index: 7158095 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.6265. Min Act: -0.1700
Data Index: 3579153 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.5327. Min Act: -0.1700
Data Index: 8489764 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.5640. Min Act: -0.1700
Data Index: 7127747 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.4390. Min Act: -0.1700
Data Index: 3972148 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.4077. Min Act: -0.1700
Data Index: 3697083 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.4390. Min Act: -0.1700
Data Index: 8240887 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.4390. Min Act: -0.1700
Data Index: 6052029 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.3765. Min Act: -0.1700
Data Index: 3359526 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.4077. Min Act: -0.1700
Data Index: 3585300 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.3765. Min Act: -0.1700
Data Index: 2276223 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3452. Min Range: -8.3452
Max Act: 7.3452. Min Act: -0.1700
Data Index: 2273218 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19