Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.6119. Min Act: -0.1700
Data Index: 2835372 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.2681. Min Act: -0.1700
Data Index: 6395642 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.2369. Min Act: -0.1700
Data Index: 6455360 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.2369. Min Act: -0.1700
Data Index: 2880299 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.1744. Min Act: -0.1700
Data Index: 7475123 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.1744. Min Act: -0.1700
Data Index: 6506229 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.1431. Min Act: -0.1700
Data Index: 6206624 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.1431. Min Act: -0.1700
Data Index: 7935536 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.0806. Min Act: -0.1700
Data Index: 3244381 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.1119. Min Act: -0.1700
Data Index: 1800864 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.1119. Min Act: -0.1700
Data Index: 3679763 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.0806. Min Act: -0.1700
Data Index: 3510013 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.0493. Min Act: -0.1700
Data Index: 6474501 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.0181. Min Act: -0.1700
Data Index: 564864 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.0181. Min Act: -0.1700
Data Index: 4130977 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.0181. Min Act: -0.1700
Data Index: 564863 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6119. Min Range: -4.6119
Max Act: 3.9868. Min Act: -0.1700
Data Index: 3540125 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.0181. Min Act: -0.1700
Data Index: 7487327 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.0181. Min Act: -0.1700
Data Index: 5630105 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6119. Min Range: -4.6119
Max Act: 4.0181. Min Act: -0.1700
Data Index: 2880808 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19