Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1058 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6798. Min Range: -8.6798
Max Act: 8.6798. Min Act: -0.1700
Data Index: 2364647 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6798. Min Range: -8.6798
Max Act: 8.3048. Min Act: -0.1700
Data Index: 4473304 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6798. Min Range: -8.6798
Max Act: 8.2423. Min Act: -0.1700
Data Index: 6064585 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6798. Min Range: -8.6798
Max Act: 8.1798. Min Act: -0.1700
Data Index: 6168278 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6798. Min Range: -8.6798
Max Act: 8.1173. Min Act: -0.1700
Data Index: 5355496 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6798. Min Range: -8.6798
Max Act: 8.0548. Min Act: -0.1700
Data Index: 695945 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6798. Min Range: -8.6798
Max Act: 8.1173. Min Act: -0.1700
Data Index: 559971 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6798. Min Range: -8.6798
Max Act: 8.1173. Min Act: -0.1700
Data Index: 6280495 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6798. Min Range: -8.6798
Max Act: 7.9923. Min Act: -0.1700
Data Index: 8378621 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6798. Min Range: -8.6798
Max Act: 8.0548. Min Act: -0.1700
Data Index: 8617191 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6798. Min Range: -8.6798
Max Act: 7.9923. Min Act: -0.1700
Data Index: 2729010 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6798. Min Range: -8.6798
Max Act: 7.9923. Min Act: -0.1700
Data Index: 3598678 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6798. Min Range: -8.6798
Max Act: 7.9923. Min Act: -0.1700
Data Index: 4720366 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6798. Min Range: -8.6798
Max Act: 7.9923. Min Act: -0.1700
Data Index: 38547 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6798. Min Range: -8.6798
Max Act: 7.9298. Min Act: -0.1700
Data Index: 2888384 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6798. Min Range: -8.6798
Max Act: 7.9298. Min Act: -0.1700
Data Index: 6425357 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6798. Min Range: -8.6798
Max Act: 7.9298. Min Act: -0.1700
Data Index: 8778703 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6798. Min Range: -8.6798
Max Act: 7.9298. Min Act: -0.1700
Data Index: 366107 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6798. Min Range: -8.6798
Max Act: 7.9923. Min Act: -0.1700
Data Index: 6483784 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6798. Min Range: -8.6798
Max Act: 7.9298. Min Act: -0.1700
Data Index: 5298887 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19