Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1521 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.5754. Min Act: -0.1700
Data Index: 6507516 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.6066. Min Act: -0.1700
Data Index: 3547255 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.6066. Min Act: -0.1700
Data Index: 8389866 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.5441. Min Act: -0.1700
Data Index: 690193 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.4816. Min Act: -0.1700
Data Index: 554836 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.4504. Min Act: -0.1700
Data Index: 40450 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.4504. Min Act: -0.1700
Data Index: 5985510 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.4504. Min Act: -0.1700
Data Index: 6265969 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.4191. Min Act: -0.1700
Data Index: 4191892 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.4504. Min Act: -0.1700
Data Index: 554818 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.4191. Min Act: -0.1700
Data Index: 3507559 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.3566. Min Act: -0.1700
Data Index: 1440536 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.3566. Min Act: -0.1700
Data Index: 2679321 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.3254. Min Act: -0.1700
Data Index: 7439913 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.3254. Min Act: -0.1700
Data Index: 876310 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.3254. Min Act: -0.1700
Data Index: 8619098 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.3254. Min Act: -0.1700
Data Index: 7179207 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.3254. Min Act: -0.1700
Data Index: 1352686 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.2941. Min Act: -0.1700
Data Index: 2298930 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6066. Min Range: -5.6066
Max Act: 5.2629. Min Act: -0.1700
Data Index: 2049986 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19