Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5556 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.7268. Min Act: -0.1700
Data Index: 6172141 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.5393. Min Act: -0.1700
Data Index: 893406 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.3830. Min Act: -0.1700
Data Index: 6714814 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.3205. Min Act: -0.1700
Data Index: 4182512 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.3205. Min Act: -0.1700
Data Index: 7928785 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.3205. Min Act: -0.1700
Data Index: 3317262 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.3205. Min Act: -0.1700
Data Index: 6503385 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.3205. Min Act: -0.1700
Data Index: 87263 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.2580. Min Act: -0.1700
Data Index: 8715666 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.2268. Min Act: -0.1700
Data Index: 1085955 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.2268. Min Act: -0.1700
Data Index: 7062929 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.2268. Min Act: -0.1700
Data Index: 330341 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.1955. Min Act: -0.1700
Data Index: 6666263 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.1955. Min Act: -0.1700
Data Index: 6669548 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.1643. Min Act: -0.1700
Data Index: 7471534 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.1955. Min Act: -0.1700
Data Index: 721271 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.2268. Min Act: -0.1700
Data Index: 770475 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.1955. Min Act: -0.1700
Data Index: 2129835 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.1955. Min Act: -0.1700
Data Index: 3410294 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7268. Min Range: -4.7268
Max Act: 4.1955. Min Act: -0.1700
Data Index: 7869816 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19