Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3525 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1881. Min Range: -6.1881
Max Act: 6.1881. Min Act: -0.1700
Data Index: 7952101 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1881. Min Range: -6.1881
Max Act: 6.1881. Min Act: -0.1700
Data Index: 6822480 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1881. Min Range: -6.1881
Max Act: 6.1256. Min Act: -0.1700
Data Index: 5154134 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1881. Min Range: -6.1881
Max Act: 6.1568. Min Act: -0.1700
Data Index: 2597066 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1881. Min Range: -6.1881
Max Act: 6.0943. Min Act: -0.1700
Data Index: 2739572 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1881. Min Range: -6.1881
Max Act: 6.0318. Min Act: -0.1700
Data Index: 2477186 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1881. Min Range: -6.1881
Max Act: 6.0631. Min Act: -0.1700
Data Index: 7303109 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1881. Min Range: -6.1881
Max Act: 6.0006. Min Act: -0.1700
Data Index: 619376 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1881. Min Range: -6.1881
Max Act: 6.0006. Min Act: -0.1700
Data Index: 619385 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1881. Min Range: -6.1881
Max Act: 5.9693. Min Act: -0.1700
Data Index: 6213191 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1881. Min Range: -6.1881
Max Act: 5.9693. Min Act: -0.1700
Data Index: 7952109 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1881. Min Range: -6.1881
Max Act: 5.9693. Min Act: -0.1700
Data Index: 3083579 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1881. Min Range: -6.1881
Max Act: 5.9381. Min Act: -0.1700
Data Index: 8690724 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1881. Min Range: -6.1881
Max Act: 5.9381. Min Act: -0.1700
Data Index: 6463504 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1881. Min Range: -6.1881
Max Act: 5.9381. Min Act: -0.1700
Data Index: 619379 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1881. Min Range: -6.1881
Max Act: 5.9381. Min Act: -0.1700
Data Index: 3738433 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1881. Min Range: -6.1881
Max Act: 5.9068. Min Act: -0.1700
Data Index: 2292314 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1881. Min Range: -6.1881
Max Act: 5.9068. Min Act: -0.1700
Data Index: 7252397 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1881. Min Range: -6.1881
Max Act: 5.9068. Min Act: -0.1700
Data Index: 5446423 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1881. Min Range: -6.1881
Max Act: 5.9068. Min Act: -0.1700
Data Index: 4366339 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19