Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2045 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4587. Min Range: -7.4587
Max Act: 7.4587. Min Act: -0.1700
Data Index: 1321328 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4587. Min Range: -7.4587
Max Act: 7.3024. Min Act: -0.1700
Data Index: 5994807 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4587. Min Range: -7.4587
Max Act: 7.2087. Min Act: -0.1700
Data Index: 8757242 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4587. Min Range: -7.4587
Max Act: 7.0837. Min Act: -0.1700
Data Index: 7583244 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4587. Min Range: -7.4587
Max Act: 7.0524. Min Act: -0.1700
Data Index: 5020874 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.9899. Min Act: -0.1700
Data Index: 5086545 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.9587. Min Act: -0.1700
Data Index: 1138903 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.9587. Min Act: -0.1700
Data Index: 2743530 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.8962. Min Act: -0.1700
Data Index: 3865878 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.8649. Min Act: -0.1700
Data Index: 1556791 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.8649. Min Act: -0.1700
Data Index: 6842589 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.8337. Min Act: -0.1700
Data Index: 7654062 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.8024. Min Act: -0.1700
Data Index: 704685 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.7712. Min Act: -0.1700
Data Index: 7992183 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.7087. Min Act: -0.1700
Data Index: 614250 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.6774. Min Act: -0.1700
Data Index: 7962619 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.7087. Min Act: -0.1700
Data Index: 6495916 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.7087. Min Act: -0.1700
Data Index: 7012145 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.6462. Min Act: -0.1700
Data Index: 6197522 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4587. Min Range: -7.4587
Max Act: 6.6462. Min Act: -0.1700
Data Index: 1300260 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19