Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3908 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.5937. Min Act: -0.1700
Data Index: 6524438 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.5624. Min Act: -0.1700
Data Index: 4044878 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4999. Min Act: -0.1700
Data Index: 6524439 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4062. Min Act: -0.1700
Data Index: 4410322 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3749. Min Act: -0.1700
Data Index: 5159909 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3437. Min Act: -0.1700
Data Index: 5958284 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3124. Min Act: -0.1700
Data Index: 8408097 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.2812. Min Act: -0.1700
Data Index: 1736341 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.2187. Min Act: -0.1700
Data Index: 3773318 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1874. Min Act: -0.1700
Data Index: 2019341 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1874. Min Act: -0.1700
Data Index: 4567549 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1874. Min Act: -0.1700
Data Index: 2709996 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1562. Min Act: -0.1700
Data Index: 6327479 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1562. Min Act: -0.1700
Data Index: 5413960 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1249. Min Act: -0.1700
Data Index: 3393910 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1249. Min Act: -0.1700
Data Index: 5902409 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1249. Min Act: -0.1700
Data Index: 2098964 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.0937. Min Act: -0.1700
Data Index: 2265073 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.0937. Min Act: -0.1700
Data Index: 8335513 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.0937. Min Act: -0.1700
Data Index: 6327480 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19