Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5106 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.6883. Min Act: -0.1700
Data Index: 6717730 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.5633. Min Act: -0.1700
Data Index: 7971436 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.2508. Min Act: -0.1700
Data Index: 972321 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.2508. Min Act: -0.1700
Data Index: 3294555 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.2508. Min Act: -0.1700
Data Index: 7327689 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.1883. Min Act: -0.1700
Data Index: 3192861 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.1883. Min Act: -0.1700
Data Index: 1644142 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.1883. Min Act: -0.1700
Data Index: 2377168 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.1258. Min Act: -0.1700
Data Index: 1040609 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.0633. Min Act: -0.1700
Data Index: 972322 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.0633. Min Act: -0.1700
Data Index: 5449867 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.0633. Min Act: -0.1700
Data Index: 5370814 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.0633. Min Act: -0.1700
Data Index: 3903729 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.0633. Min Act: -0.1700
Data Index: 3192863 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.0633. Min Act: -0.1700
Data Index: 8705463 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.0633. Min Act: -0.1700
Data Index: 497532 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.0633. Min Act: -0.1700
Data Index: 5783162 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.0008. Min Act: -0.1700
Data Index: 4686078 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.0008. Min Act: -0.1700
Data Index: 1123913 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6883. Min Range: -9.6883
Max Act: 9.0008. Min Act: -0.1700
Data Index: 8705464 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19