Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1188. Min Range: -3.1188
Max Act: 3.1188. Min Act: -0.1700
Data Index: 2752150 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1188. Min Range: -3.1188
Max Act: 3.0873. Min Act: -0.1700
Data Index: 190692 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1188. Min Range: -3.1188
Max Act: 3.0558. Min Act: -0.1700
Data Index: 222132 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1188. Min Range: -3.1188
Max Act: 3.0242. Min Act: -0.1700
Data Index: 6440191 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.9926. Min Act: -0.1700
Data Index: 2499788 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.9768. Min Act: -0.1700
Data Index: 1279420 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.9768. Min Act: -0.1700
Data Index: 5773927 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.9451. Min Act: -0.1700
Data Index: 3070430 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.9451. Min Act: -0.1700
Data Index: 4814707 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.9134. Min Act: -0.1700
Data Index: 6328482 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.9134. Min Act: -0.1700
Data Index: 7337873 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.8817. Min Act: -0.1700
Data Index: 2752146 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.8500. Min Act: -0.1700
Data Index: 3163213 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.8341. Min Act: -0.1700
Data Index: 919065 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.8341. Min Act: -0.1700
Data Index: 2859836 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.8182. Min Act: -0.1700
Data Index: 2859833 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.8022. Min Act: -0.1700
Data Index: 6328489 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.7863. Min Act: -0.1700
Data Index: 4527090 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.7863. Min Act: -0.1700
Data Index: 2859834 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1188. Min Range: -3.1188
Max Act: 2.7704. Min Act: -0.1700
Data Index: 3127676 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19