Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6199 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.9924. Min Act: -0.1700
Data Index: 2071913 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1174. Min Range: -9.1174
Max Act: 9.1174. Min Act: -0.1700
Data Index: 84479 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1174. Min Range: -9.1174
Max Act: 9.0549. Min Act: -0.1700
Data Index: 3096352 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.8674. Min Act: -0.1700
Data Index: 1845764 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.8049. Min Act: -0.1700
Data Index: 6664937 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.7424. Min Act: -0.1700
Data Index: 5159355 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.7424. Min Act: -0.1700
Data Index: 4336003 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.7424. Min Act: -0.1700
Data Index: 36930 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.7424. Min Act: -0.1700
Data Index: 7212269 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.7424. Min Act: -0.1700
Data Index: 7189225 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.7424. Min Act: -0.1700
Data Index: 4667126 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.6799. Min Act: -0.1700
Data Index: 7734867 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.6799. Min Act: -0.1700
Data Index: 4981162 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.6174. Min Act: -0.1700
Data Index: 2711354 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.5549. Min Act: -0.1700
Data Index: 443034 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.6174. Min Act: -0.1700
Data Index: 1812940 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.5549. Min Act: -0.1700
Data Index: 3955691 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.5549. Min Act: -0.1700
Data Index: 3734944 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.5549. Min Act: -0.1700
Data Index: 659287 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1174. Min Range: -9.1174
Max Act: 8.5549. Min Act: -0.1700
Data Index: 7189218 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19