Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2321 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.9563. Min Act: -0.1700
Data Index: 4808667 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.8625. Min Act: -0.1700
Data Index: 117313 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.8313. Min Act: -0.1700
Data Index: 4904980 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.6750. Min Act: -0.1700
Data Index: 4610328 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.5813. Min Act: -0.1700
Data Index: 1773596 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.5813. Min Act: -0.1700
Data Index: 7858802 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.3938. Min Act: -0.1700
Data Index: 4318580 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.3313. Min Act: -0.1700
Data Index: 687641 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.3000. Min Act: -0.1700
Data Index: 8442498 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.2688. Min Act: -0.1700
Data Index: 4119151 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.2063. Min Act: -0.1700
Data Index: 952077 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.1750. Min Act: -0.1700
Data Index: 6967450 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.1750. Min Act: -0.1700
Data Index: 3830341 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.1438. Min Act: -0.1700
Data Index: 1473261 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.1125. Min Act: -0.1700
Data Index: 7964741 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.1125. Min Act: -0.1700
Data Index: 3830738 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.1125. Min Act: -0.1700
Data Index: 1989360 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9563. Min Range: -6.9563
Max Act: 6.0500. Min Act: -0.1700
Data Index: 7506916 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9563. Min Range: -6.9563
Max Act: 5.9875. Min Act: -0.1700
Data Index: 4375271 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9563. Min Range: -6.9563
Max Act: 5.9563. Min Act: -0.1700
Data Index: 6930221 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19