Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5858 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0104. Min Range: -6.0104
Max Act: 6.0104. Min Act: -0.1700
Data Index: 3825554 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.9791. Min Act: -0.1700
Data Index: 7490780 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.9479. Min Act: -0.1700
Data Index: 6127115 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.8229. Min Act: -0.1700
Data Index: 3119856 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.8229. Min Act: -0.1700
Data Index: 1295498 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.8229. Min Act: -0.1700
Data Index: 2619972 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.8229. Min Act: -0.1700
Data Index: 4367524 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.7604. Min Act: -0.1700
Data Index: 6463782 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.7604. Min Act: -0.1700
Data Index: 8192053 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.7604. Min Act: -0.1700
Data Index: 2921305 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.7604. Min Act: -0.1700
Data Index: 6597105 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.7604. Min Act: -0.1700
Data Index: 3096223 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.7291. Min Act: -0.1700
Data Index: 1048690 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.7604. Min Act: -0.1700
Data Index: 4696019 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.6979. Min Act: -0.1700
Data Index: 779727 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.6979. Min Act: -0.1700
Data Index: 3083358 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.6979. Min Act: -0.1700
Data Index: 4281759 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.6666. Min Act: -0.1700
Data Index: 7446040 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.6666. Min Act: -0.1700
Data Index: 8612738 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0104. Min Range: -6.0104
Max Act: 5.6354. Min Act: -0.1700
Data Index: 5238705 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19