Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0048. Min Range: -7.0048
Max Act: 7.0048. Min Act: -0.1700
Data Index: 8181557 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.7861. Min Act: -0.1700
Data Index: 4717601 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.5986. Min Act: -0.1700
Data Index: 4380874 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.5673. Min Act: -0.1700
Data Index: 4669820 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.4736. Min Act: -0.1700
Data Index: 883551 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.4423. Min Act: -0.1700
Data Index: 6637390 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.3798. Min Act: -0.1700
Data Index: 7915099 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.3486. Min Act: -0.1700
Data Index: 4385478 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.3173. Min Act: -0.1700
Data Index: 3277948 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.2548. Min Act: -0.1700
Data Index: 8735853 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.2548. Min Act: -0.1700
Data Index: 7719815 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.1611. Min Act: -0.1700
Data Index: 4014 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.1611. Min Act: -0.1700
Data Index: 6212208 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.0986. Min Act: -0.1700
Data Index: 1749194 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.0986. Min Act: -0.1700
Data Index: 8257599 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.0673. Min Act: -0.1700
Data Index: 5044812 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.0673. Min Act: -0.1700
Data Index: 2265797 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.0048. Min Act: -0.1700
Data Index: 1628079 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0048. Min Range: -7.0048
Max Act: 6.0361. Min Act: -0.1700
Data Index: 3730055 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0048. Min Range: -7.0048
Max Act: 5.9736. Min Act: -0.1700
Data Index: 4719971 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19