Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 758 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.5182. Min Act: -0.1700
Data Index: 695870 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.4557. Min Act: -0.1700
Data Index: 6180509 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.3932. Min Act: -0.1700
Data Index: 7100628 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.3932. Min Act: -0.1700
Data Index: 5122757 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.3620. Min Act: -0.1700
Data Index: 3214737 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.3307. Min Act: -0.1700
Data Index: 5163085 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.2995. Min Act: -0.1700
Data Index: 2196891 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.2682. Min Act: -0.1700
Data Index: 4506922 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.2682. Min Act: -0.1700
Data Index: 5049240 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.2682. Min Act: -0.1700
Data Index: 4943400 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.2682. Min Act: -0.1700
Data Index: 83055 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.2682. Min Act: -0.1700
Data Index: 2729354 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.2370. Min Act: -0.1700
Data Index: 6505669 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.1745. Min Act: -0.1700
Data Index: 5747209 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.1745. Min Act: -0.1700
Data Index: 1531375 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.1745. Min Act: -0.1700
Data Index: 775868 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.1745. Min Act: -0.1700
Data Index: 859369 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.1432. Min Act: -0.1700
Data Index: 6570828 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.1120. Min Act: -0.1700
Data Index: 6279934 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5182. Min Range: -5.5182
Max Act: 5.1745. Min Act: -0.1700
Data Index: 5085126 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19