Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 981 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.8923. Min Act: -0.1700
Data Index: 6737536 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.8610. Min Act: -0.1700
Data Index: 1349436 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.8923. Min Act: -0.1700
Data Index: 83353 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.8298. Min Act: -0.1700
Data Index: 6034610 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.8298. Min Act: -0.1700
Data Index: 4113941 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7985. Min Act: -0.1700
Data Index: 751489 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7985. Min Act: -0.1700
Data Index: 3445714 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7360. Min Act: -0.1700
Data Index: 5002852 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7673. Min Act: -0.1700
Data Index: 7031007 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7360. Min Act: -0.1700
Data Index: 7400680 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7673. Min Act: -0.1700
Data Index: 8316648 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7360. Min Act: -0.1700
Data Index: 6654584 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7673. Min Act: -0.1700
Data Index: 2808930 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7048. Min Act: -0.1700
Data Index: 2373863 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7048. Min Act: -0.1700
Data Index: 3679238 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7048. Min Act: -0.1700
Data Index: 1564273 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7048. Min Act: -0.1700
Data Index: 1194812 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.7048. Min Act: -0.1700
Data Index: 1699937 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.6735. Min Act: -0.1700
Data Index: 1003278 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.6423. Min Act: -0.1700
Data Index: 485421 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19