Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2066 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3767. Min Range: -7.3767
Max Act: 7.3767. Min Act: -0.1700
Data Index: 488937 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3767. Min Range: -7.3767
Max Act: 7.3454. Min Act: -0.1700
Data Index: 478394 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3767. Min Range: -7.3767
Max Act: 7.0642. Min Act: -0.1700
Data Index: 3535308 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3767. Min Range: -7.3767
Max Act: 7.0642. Min Act: -0.1700
Data Index: 3921758 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3767. Min Range: -7.3767
Max Act: 7.0642. Min Act: -0.1700
Data Index: 6684772 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3767. Min Range: -7.3767
Max Act: 7.0642. Min Act: -0.1700
Data Index: 1350204 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3767. Min Range: -7.3767
Max Act: 7.0329. Min Act: -0.1700
Data Index: 8675821 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.9392. Min Act: -0.1700
Data Index: 1113589 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.9079. Min Act: -0.1700
Data Index: 7598523 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.9079. Min Act: -0.1700
Data Index: 4435938 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.8142. Min Act: -0.1700
Data Index: 3909808 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.7829. Min Act: -0.1700
Data Index: 5498419 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.7829. Min Act: -0.1700
Data Index: 2638569 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.7829. Min Act: -0.1700
Data Index: 302669 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.7517. Min Act: -0.1700
Data Index: 1079120 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.7517. Min Act: -0.1700
Data Index: 6930144 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.7517. Min Act: -0.1700
Data Index: 7430184 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.7517. Min Act: -0.1700
Data Index: 1036812 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.7204. Min Act: -0.1700
Data Index: 3126029 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3767. Min Range: -7.3767
Max Act: 6.7204. Min Act: -0.1700
Data Index: 1881650 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19