Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5375 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.6440. Min Act: -0.1700
Data Index: 3593632 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.3940. Min Act: -0.1700
Data Index: 3982289 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.3940. Min Act: -0.1700
Data Index: 2648286 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.3315. Min Act: -0.1700
Data Index: 2161649 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.3002. Min Act: -0.1700
Data Index: 4205885 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.3002. Min Act: -0.1700
Data Index: 5326574 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.2690. Min Act: -0.1700
Data Index: 65250 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.2065. Min Act: -0.1700
Data Index: 5195012 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.2377. Min Act: -0.1700
Data Index: 8245245 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.1752. Min Act: -0.1700
Data Index: 3982291 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.1440. Min Act: -0.1700
Data Index: 5893699 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.0502. Min Act: -0.1700
Data Index: 6588768 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.0815. Min Act: -0.1700
Data Index: 4205887 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.0502. Min Act: -0.1700
Data Index: 7401341 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.0502. Min Act: -0.1700
Data Index: 3366888 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.0815. Min Act: -0.1700
Data Index: 8754059 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.0502. Min Act: -0.1700
Data Index: 7220321 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.0190. Min Act: -0.1700
Data Index: 7471162 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.0190. Min Act: -0.1700
Data Index: 4175632 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6440. Min Range: -7.6440
Max Act: 7.0502. Min Act: -0.1700
Data Index: 6676913 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19