Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6311. Min Range: -7.6311
Max Act: 7.6311. Min Act: -0.1700
Data Index: 6491443 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6311. Min Range: -7.6311
Max Act: 7.3811. Min Act: -0.1700
Data Index: 5645632 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6311. Min Range: -7.6311
Max Act: 7.2249. Min Act: -0.1700
Data Index: 4289318 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6311. Min Range: -7.6311
Max Act: 7.1936. Min Act: -0.1700
Data Index: 1587012 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6311. Min Range: -7.6311
Max Act: 7.0999. Min Act: -0.1700
Data Index: 4543597 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6311. Min Range: -7.6311
Max Act: 7.0686. Min Act: -0.1700
Data Index: 5316485 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.9124. Min Act: -0.1700
Data Index: 6570481 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.9124. Min Act: -0.1700
Data Index: 833504 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.8186. Min Act: -0.1700
Data Index: 2224038 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.7874. Min Act: -0.1700
Data Index: 5874118 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.7561. Min Act: -0.1700
Data Index: 3616385 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.7561. Min Act: -0.1700
Data Index: 4230143 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.7561. Min Act: -0.1700
Data Index: 5183879 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.7249. Min Act: -0.1700
Data Index: 3991540 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.6936. Min Act: -0.1700
Data Index: 4340500 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.6936. Min Act: -0.1700
Data Index: 6640060 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.6936. Min Act: -0.1700
Data Index: 7692941 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.6936. Min Act: -0.1700
Data Index: 6467498 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.6624. Min Act: -0.1700
Data Index: 2171661 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6311. Min Range: -7.6311
Max Act: 6.6624. Min Act: -0.1700
Data Index: 3783014 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19