Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 732 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.9016. Min Act: -0.1700
Data Index: 4665624 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.8391. Min Act: -0.1700
Data Index: 6418704 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.8391. Min Act: -0.1700
Data Index: 2024312 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.8391. Min Act: -0.1700
Data Index: 7035011 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.7141. Min Act: -0.1700
Data Index: 332697 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.7141. Min Act: -0.1700
Data Index: 4316620 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.7141. Min Act: -0.1700
Data Index: 7197045 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.6516. Min Act: -0.1700
Data Index: 8098324 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.6516. Min Act: -0.1700
Data Index: 6885500 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.6516. Min Act: -0.1700
Data Index: 5041387 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.5891. Min Act: -0.1700
Data Index: 4639352 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.6516. Min Act: -0.1700
Data Index: 3270894 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.5891. Min Act: -0.1700
Data Index: 6827955 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.5266. Min Act: -0.1700
Data Index: 2611315 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.5266. Min Act: -0.1700
Data Index: 1371431 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.5266. Min Act: -0.1700
Data Index: 5041390 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.5266. Min Act: -0.1700
Data Index: 5480619 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.4641. Min Act: -0.1700
Data Index: 2621436 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.4016. Min Act: -0.1700
Data Index: 1656844 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9016. Min Range: -8.9016
Max Act: 8.4016. Min Act: -0.1700
Data Index: 4319521 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19