Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.9206. Min Act: -0.1700
Data Index: 903115 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.8581. Min Act: -0.1700
Data Index: 5255236 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.7643. Min Act: -0.1700
Data Index: 582341 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.7018. Min Act: -0.1700
Data Index: 8601791 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.7018. Min Act: -0.1700
Data Index: 8156750 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.7018. Min Act: -0.1700
Data Index: 6936844 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.6706. Min Act: -0.1700
Data Index: 4472059 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.6706. Min Act: -0.1700
Data Index: 2612610 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.6706. Min Act: -0.1700
Data Index: 53340 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.6706. Min Act: -0.1700
Data Index: 1484336 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.6081. Min Act: -0.1700
Data Index: 8082643 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.6393. Min Act: -0.1700
Data Index: 4379283 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.6081. Min Act: -0.1700
Data Index: 4736510 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.6081. Min Act: -0.1700
Data Index: 1202042 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.5768. Min Act: -0.1700
Data Index: 2042616 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.5768. Min Act: -0.1700
Data Index: 3663494 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.5768. Min Act: -0.1700
Data Index: 1543756 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.5768. Min Act: -0.1700
Data Index: 5251872 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.6081. Min Act: -0.1700
Data Index: 3484653 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9206. Min Range: -6.9206
Max Act: 6.5768. Min Act: -0.1700
Data Index: 561161 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19