Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2509 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0097. Min Range: -8.0097
Max Act: 8.0097. Min Act: -0.1700
Data Index: 7503830 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.9472. Min Act: -0.1700
Data Index: 4499751 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.8847. Min Act: -0.1700
Data Index: 7791242 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.6972. Min Act: -0.1700
Data Index: 1635409 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.6347. Min Act: -0.1700
Data Index: 1701066 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.5722. Min Act: -0.1700
Data Index: 8700228 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.5722. Min Act: -0.1700
Data Index: 6020607 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.5722. Min Act: -0.1700
Data Index: 6137647 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.5097. Min Act: -0.1700
Data Index: 8004249 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.5097. Min Act: -0.1700
Data Index: 2143740 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.5097. Min Act: -0.1700
Data Index: 3096875 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.4472. Min Act: -0.1700
Data Index: 7668381 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.4472. Min Act: -0.1700
Data Index: 3721902 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.4472. Min Act: -0.1700
Data Index: 7814467 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.3847. Min Act: -0.1700
Data Index: 7891093 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.3847. Min Act: -0.1700
Data Index: 2387471 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.3847. Min Act: -0.1700
Data Index: 3055046 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.3847. Min Act: -0.1700
Data Index: 6559171 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.3847. Min Act: -0.1700
Data Index: 3722861 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0097. Min Range: -8.0097
Max Act: 7.3847. Min Act: -0.1700
Data Index: 4331255 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19