Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.6061. Min Act: -0.1700
Data Index: 2604125 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.4186. Min Act: -0.1700
Data Index: 6899136 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.4186. Min Act: -0.1700
Data Index: 7883039 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.4186. Min Act: -0.1700
Data Index: 3731930 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3873. Min Act: -0.1700
Data Index: 4650715 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3873. Min Act: -0.1700
Data Index: 7549392 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3873. Min Act: -0.1700
Data Index: 491012 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3561. Min Act: -0.1700
Data Index: 5329270 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3561. Min Act: -0.1700
Data Index: 4316156 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3561. Min Act: -0.1700
Data Index: 235598 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3561. Min Act: -0.1700
Data Index: 4608392 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3561. Min Act: -0.1700
Data Index: 21878 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3561. Min Act: -0.1700
Data Index: 8259190 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3561. Min Act: -0.1700
Data Index: 8511565 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3561. Min Act: -0.1700
Data Index: 6353498 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3248. Min Act: -0.1700
Data Index: 8223114 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.3248. Min Act: -0.1700
Data Index: 4903871 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.2623. Min Act: -0.1700
Data Index: 6504716 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.2936. Min Act: -0.1700
Data Index: 1077128 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6061. Min Range: -4.6061
Max Act: 4.2623. Min Act: -0.1700
Data Index: 3612974 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19