Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 514 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.3850. Min Act: -0.1700
Data Index: 6911802 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.3538. Min Act: -0.1700
Data Index: 6911806 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.2913. Min Act: -0.1700
Data Index: 8403208 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.2913. Min Act: -0.1700
Data Index: 8403207 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.2600. Min Act: -0.1700
Data Index: 6789874 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.2600. Min Act: -0.1700
Data Index: 2161102 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.2288. Min Act: -0.1700
Data Index: 4915864 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.2288. Min Act: -0.1700
Data Index: 2161101 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.2288. Min Act: -0.1700
Data Index: 8087579 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.2288. Min Act: -0.1700
Data Index: 5495113 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.1975. Min Act: -0.1700
Data Index: 8403211 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.1663. Min Act: -0.1700
Data Index: 6229903 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.1663. Min Act: -0.1700
Data Index: 5116384 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.1975. Min Act: -0.1700
Data Index: 4915865 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.1663. Min Act: -0.1700
Data Index: 4992174 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.1663. Min Act: -0.1700
Data Index: 6911807 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.1663. Min Act: -0.1700
Data Index: 2706760 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.1663. Min Act: -0.1700
Data Index: 6214900 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.1663. Min Act: -0.1700
Data Index: 491198 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3850. Min Range: -5.3850
Max Act: 5.1663. Min Act: -0.1700
Data Index: 5849280 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19