Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 757 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.8410. Min Act: -0.1700
Data Index: 6116117 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.6535. Min Act: -0.1700
Data Index: 5687694 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.5598. Min Act: -0.1700
Data Index: 1888106 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4973. Min Act: -0.1700
Data Index: 7642012 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4660. Min Act: -0.1700
Data Index: 8495137 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4660. Min Act: -0.1700
Data Index: 3340564 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4348. Min Act: -0.1700
Data Index: 1789340 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4348. Min Act: -0.1700
Data Index: 5175027 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4348. Min Act: -0.1700
Data Index: 8011133 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4660. Min Act: -0.1700
Data Index: 3890279 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4348. Min Act: -0.1700
Data Index: 7837350 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4035. Min Act: -0.1700
Data Index: 6140325 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4035. Min Act: -0.1700
Data Index: 6354961 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.3723. Min Act: -0.1700
Data Index: 5375838 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.3410. Min Act: -0.1700
Data Index: 6435958 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.3410. Min Act: -0.1700
Data Index: 3071720 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.3410. Min Act: -0.1700
Data Index: 1888103 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.3410. Min Act: -0.1700
Data Index: 3160740 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.3098. Min Act: -0.1700
Data Index: 200251 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.3098. Min Act: -0.1700
Data Index: 5674430 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19