Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1863 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.9370. Min Act: -0.1700
Data Index: 7112533 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.9058. Min Act: -0.1700
Data Index: 2014078 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8745. Min Act: -0.1700
Data Index: 2898413 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8745. Min Act: -0.1700
Data Index: 1721404 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8745. Min Act: -0.1700
Data Index: 1691099 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8745. Min Act: -0.1700
Data Index: 1197014 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8745. Min Act: -0.1700
Data Index: 3940647 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8745. Min Act: -0.1700
Data Index: 5453224 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8432. Min Act: -0.1700
Data Index: 7825873 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8432. Min Act: -0.1700
Data Index: 7443172 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8119. Min Act: -0.1700
Data Index: 8016524 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8119. Min Act: -0.1700
Data Index: 6258860 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8432. Min Act: -0.1700
Data Index: 2021649 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8432. Min Act: -0.1700
Data Index: 8600169 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8119. Min Act: -0.1700
Data Index: 2659815 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8119. Min Act: -0.1700
Data Index: 4966741 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8119. Min Act: -0.1700
Data Index: 5048453 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8119. Min Act: -0.1700
Data Index: 2364127 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8119. Min Act: -0.1700
Data Index: 2422983 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9370. Min Range: -3.9370
Max Act: 3.8119. Min Act: -0.1700
Data Index: 112552 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19