Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.7115. Min Act: -0.1700
Data Index: 205891 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.6489. Min Act: -0.1700
Data Index: 8579398 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5863. Min Act: -0.1700
Data Index: 3591152 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5863. Min Act: -0.1700
Data Index: 7669285 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5863. Min Act: -0.1700
Data Index: 1347688 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5550. Min Act: -0.1700
Data Index: 2332507 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5550. Min Act: -0.1700
Data Index: 1348170 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5550. Min Act: -0.1700
Data Index: 5288776 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5550. Min Act: -0.1700
Data Index: 2853436 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5550. Min Act: -0.1700
Data Index: 2851269 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5237. Min Act: -0.1700
Data Index: 4748067 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5237. Min Act: -0.1700
Data Index: 5282366 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5237. Min Act: -0.1700
Data Index: 46667 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5237. Min Act: -0.1700
Data Index: 2901976 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5237. Min Act: -0.1700
Data Index: 6336484 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5237. Min Act: -0.1700
Data Index: 3435436 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5237. Min Act: -0.1700
Data Index: 4610489 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5237. Min Act: -0.1700
Data Index: 823266 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5237. Min Act: -0.1700
Data Index: 3724035 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7115. Min Range: -3.7115
Max Act: 3.5237. Min Act: -0.1700
Data Index: 4431541 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19