Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2423. Min Range: -8.2423
Max Act: 8.2423. Min Act: -0.1700
Data Index: 5208890 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2423. Min Range: -8.2423
Max Act: 8.1798. Min Act: -0.1700
Data Index: 2205090 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2423. Min Range: -8.2423
Max Act: 8.1798. Min Act: -0.1700
Data Index: 4844989 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2423. Min Range: -8.2423
Max Act: 8.1798. Min Act: -0.1700
Data Index: 1345146 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2423. Min Range: -8.2423
Max Act: 8.1798. Min Act: -0.1700
Data Index: 2275186 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2423. Min Range: -8.2423
Max Act: 8.2423. Min Act: -0.1700
Data Index: 5733027 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2423. Min Range: -8.2423
Max Act: 8.1798. Min Act: -0.1700
Data Index: 6594754 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2423. Min Range: -8.2423
Max Act: 8.0860. Min Act: -0.1700
Data Index: 68203 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2423. Min Range: -8.2423
Max Act: 8.0548. Min Act: -0.1700
Data Index: 5704769 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2423. Min Range: -8.2423
Max Act: 7.9610. Min Act: -0.1700
Data Index: 7761368 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2423. Min Range: -8.2423
Max Act: 7.9923. Min Act: -0.1700
Data Index: 1168013 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2423. Min Range: -8.2423
Max Act: 7.9923. Min Act: -0.1700
Data Index: 4792791 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2423. Min Range: -8.2423
Max Act: 7.9923. Min Act: -0.1700
Data Index: 8826270 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2423. Min Range: -8.2423
Max Act: 8.0235. Min Act: -0.1700
Data Index: 2688665 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2423. Min Range: -8.2423
Max Act: 7.9610. Min Act: -0.1700
Data Index: 4233426 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2423. Min Range: -8.2423
Max Act: 7.9923. Min Act: -0.1700
Data Index: 5650852 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2423. Min Range: -8.2423
Max Act: 7.8673. Min Act: -0.1700
Data Index: 1356002 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2423. Min Range: -8.2423
Max Act: 7.9298. Min Act: -0.1700
Data Index: 1925218 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2423. Min Range: -8.2423
Max Act: 7.8985. Min Act: -0.1700
Data Index: 726280 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2423. Min Range: -8.2423
Max Act: 7.8985. Min Act: -0.1700
Data Index: 7605095 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19