Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 215 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6660. Min Range: -9.6660
Max Act: 9.6660. Min Act: -0.1700
Data Index: 1577242 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6660. Min Range: -9.6660
Max Act: 9.4160. Min Act: -0.1700
Data Index: 4993931 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6660. Min Range: -9.6660
Max Act: 9.1035. Min Act: -0.1700
Data Index: 2937764 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6660. Min Range: -9.6660
Max Act: 9.0410. Min Act: -0.1700
Data Index: 3837411 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.9785. Min Act: -0.1700
Data Index: 4662930 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.9785. Min Act: -0.1700
Data Index: 7564177 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.9785. Min Act: -0.1700
Data Index: 6995658 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.9160. Min Act: -0.1700
Data Index: 8832714 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.9160. Min Act: -0.1700
Data Index: 8013842 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.9785. Min Act: -0.1700
Data Index: 1935239 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.9160. Min Act: -0.1700
Data Index: 5268549 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.8535. Min Act: -0.1700
Data Index: 6398097 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.8535. Min Act: -0.1700
Data Index: 3394785 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.8535. Min Act: -0.1700
Data Index: 2435233 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.8535. Min Act: -0.1700
Data Index: 4206721 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.8535. Min Act: -0.1700
Data Index: 2646372 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.8535. Min Act: -0.1700
Data Index: 4178061 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.8535. Min Act: -0.1700
Data Index: 4907795 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.8535. Min Act: -0.1700
Data Index: 2345646 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6660. Min Range: -9.6660
Max Act: 8.8535. Min Act: -0.1700
Data Index: 7358431 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19