Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3786 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.7501. Min Act: -0.1700
Data Index: 7580719 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.6876. Min Act: -0.1700
Data Index: 6410791 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.6564. Min Act: -0.1700
Data Index: 5807741 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.6251. Min Act: -0.1700
Data Index: 7369971 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.6251. Min Act: -0.1700
Data Index: 899134 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.6251. Min Act: -0.1700
Data Index: 5010255 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.5939. Min Act: -0.1700
Data Index: 4006714 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.5626. Min Act: -0.1700
Data Index: 1755074 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.4689. Min Act: -0.1700
Data Index: 6001803 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.5001. Min Act: -0.1700
Data Index: 504447 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.4689. Min Act: -0.1700
Data Index: 5616408 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.4689. Min Act: -0.1700
Data Index: 1979612 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.4689. Min Act: -0.1700
Data Index: 3451829 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.4376. Min Act: -0.1700
Data Index: 4672266 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.4064. Min Act: -0.1700
Data Index: 5180249 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.4064. Min Act: -0.1700
Data Index: 4420726 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.4064. Min Act: -0.1700
Data Index: 5944686 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.4064. Min Act: -0.1700
Data Index: 5226091 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.4064. Min Act: -0.1700
Data Index: 3527494 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7501. Min Range: -6.7501
Max Act: 6.4064. Min Act: -0.1700
Data Index: 65176 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19