Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1663 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.9423. Min Act: -0.1700
Data Index: 85943 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.4423. Min Act: -0.1700
Data Index: 5659955 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.3798. Min Act: -0.1700
Data Index: 4389834 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.3798. Min Act: -0.1700
Data Index: 8469676 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.2548. Min Act: -0.1700
Data Index: 3000500 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.2548. Min Act: -0.1700
Data Index: 6057427 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.1923. Min Act: -0.1700
Data Index: 1990892 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.1298. Min Act: -0.1700
Data Index: 6667679 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.1298. Min Act: -0.1700
Data Index: 1171970 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.1298. Min Act: -0.1700
Data Index: 120059 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.0673. Min Act: -0.1700
Data Index: 8772918 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.0673. Min Act: -0.1700
Data Index: 4389835 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.0673. Min Act: -0.1700
Data Index: 1494234 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.0673. Min Act: -0.1700
Data Index: 2466021 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.0673. Min Act: -0.1700
Data Index: 7705482 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9423. Min Range: -8.9423
Max Act: 7.9423. Min Act: -0.1700
Data Index: 5879923 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.0048. Min Act: -0.1700
Data Index: 3811037 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9423. Min Range: -8.9423
Max Act: 8.0048. Min Act: -0.1700
Data Index: 6852125 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9423. Min Range: -8.9423
Max Act: 7.9423. Min Act: -0.1700
Data Index: 6456409 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9423. Min Range: -8.9423
Max Act: 7.8798. Min Act: -0.1700
Data Index: 2956678 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19