Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3269 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0144. Min Range: -6.0144
Max Act: 6.0144. Min Act: -0.1700
Data Index: 795444 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0144. Min Range: -6.0144
Max Act: 6.0144. Min Act: -0.1700
Data Index: 463815 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.9832. Min Act: -0.1700
Data Index: 5501989 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.9207. Min Act: -0.1700
Data Index: 6171528 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.8894. Min Act: -0.1700
Data Index: 7141790 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.8269. Min Act: -0.1700
Data Index: 1622896 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.8269. Min Act: -0.1700
Data Index: 5160204 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.7957. Min Act: -0.1700
Data Index: 3156423 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.7644. Min Act: -0.1700
Data Index: 4823388 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.7644. Min Act: -0.1700
Data Index: 3214685 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.7332. Min Act: -0.1700
Data Index: 6148724 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.6707. Min Act: -0.1700
Data Index: 8199572 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.7019. Min Act: -0.1700
Data Index: 4367392 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.7332. Min Act: -0.1700
Data Index: 993344 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.7019. Min Act: -0.1700
Data Index: 3918432 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.7019. Min Act: -0.1700
Data Index: 4367387 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.6707. Min Act: -0.1700
Data Index: 950983 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.6707. Min Act: -0.1700
Data Index: 5355170 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.6394. Min Act: -0.1700
Data Index: 5621325 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0144. Min Range: -6.0144
Max Act: 5.6082. Min Act: -0.1700
Data Index: 7397299 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19