Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1477 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0626. Min Range: -6.0626
Max Act: 6.0626. Min Act: -0.1700
Data Index: 4888062 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0626. Min Range: -6.0626
Max Act: 6.0001. Min Act: -0.1698
Data Index: 3570025 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.9688. Min Act: -0.1700
Data Index: 3102737 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.9688. Min Act: -0.1700
Data Index: 2654862 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.9688. Min Act: -0.1700
Data Index: 4620437 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.9063. Min Act: -0.1700
Data Index: 2955369 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.9063. Min Act: -0.1700
Data Index: 497173 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.9063. Min Act: -0.1700
Data Index: 3977604 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.8751. Min Act: -0.1700
Data Index: 7908267 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.8751. Min Act: -0.1700
Data Index: 3885042 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.8438. Min Act: -0.1700
Data Index: 2457968 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.8126. Min Act: -0.1700
Data Index: 358333 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.8126. Min Act: -0.1700
Data Index: 8387687 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.8126. Min Act: -0.1700
Data Index: 5823313 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.8126. Min Act: -0.1700
Data Index: 6707756 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.7813. Min Act: -0.1700
Data Index: 4956104 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.7813. Min Act: -0.1700
Data Index: 7549023 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.7501. Min Act: -0.1700
Data Index: 6645643 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.7501. Min Act: -0.1700
Data Index: 3589857 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0626. Min Range: -6.0626
Max Act: 5.7813. Min Act: -0.1700
Data Index: 590964 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19