Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4456 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3235. Min Range: -6.3235
Max Act: 6.3235. Min Act: -0.1700
Data Index: 5248959 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3235. Min Range: -6.3235
Max Act: 6.2298. Min Act: -0.1700
Data Index: 3397674 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3235. Min Range: -6.3235
Max Act: 6.0735. Min Act: -0.1700
Data Index: 7242724 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3235. Min Range: -6.3235
Max Act: 6.0423. Min Act: -0.1700
Data Index: 947658 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3235. Min Range: -6.3235
Max Act: 6.0423. Min Act: -0.1700
Data Index: 1393934 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.8548. Min Act: -0.1700
Data Index: 1984480 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.8235. Min Act: -0.1700
Data Index: 1823038 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.8235. Min Act: -0.1700
Data Index: 4123614 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.8235. Min Act: -0.1700
Data Index: 5102891 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.7923. Min Act: -0.1700
Data Index: 5630949 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.7610. Min Act: -0.1700
Data Index: 760108 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.7923. Min Act: -0.1700
Data Index: 2819766 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.6985. Min Act: -0.1700
Data Index: 2955095 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.6985. Min Act: -0.1700
Data Index: 7020763 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.6985. Min Act: -0.1700
Data Index: 7753539 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.6985. Min Act: -0.1700
Data Index: 2593558 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.6673. Min Act: -0.1700
Data Index: 6533989 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.6673. Min Act: -0.1700
Data Index: 5381469 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.6360. Min Act: -0.1700
Data Index: 1393935 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3235. Min Range: -6.3235
Max Act: 5.6673. Min Act: -0.1700
Data Index: 8273335 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19