Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1817 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.8747. Min Act: -0.1700
Data Index: 6688879 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.8429. Min Act: -0.1700
Data Index: 7912112 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.7792. Min Act: -0.1700
Data Index: 3131795 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6994. Min Act: -0.1700
Data Index: 467127 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 539210 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 1248716 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 1369295 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 1183204 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 1600404 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 672143 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6673. Min Act: -0.1700
Data Index: 1337237 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 1532991 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 998513 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 82876 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 47277 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 907055 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 381689 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 374521 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 352372 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8747. Min Range: -2.8747
Max Act: 2.6834. Min Act: -0.1700
Data Index: 1448098 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19