Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0673. Min Range: -6.0673
Max Act: 6.0673. Min Act: -0.1700
Data Index: 256880 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0673. Min Range: -6.0673
Max Act: 6.0048. Min Act: -0.1700
Data Index: 3071650 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.9423. Min Act: -0.1700
Data Index: 8096045 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.8798. Min Act: -0.1700
Data Index: 1333549 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.8173. Min Act: -0.1700
Data Index: 5056013 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.7860. Min Act: -0.1700
Data Index: 7225671 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.7860. Min Act: -0.1700
Data Index: 785408 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.7235. Min Act: -0.1700
Data Index: 3180201 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.6923. Min Act: -0.1700
Data Index: 5278716 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.6610. Min Act: -0.1700
Data Index: 1675298 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.6610. Min Act: -0.1700
Data Index: 62600 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.6610. Min Act: -0.1700
Data Index: 6708397 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.6610. Min Act: -0.1700
Data Index: 8777222 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.5985. Min Act: -0.1700
Data Index: 5917682 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.5985. Min Act: -0.1700
Data Index: 6084272 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.5673. Min Act: -0.1700
Data Index: 4220890 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.5673. Min Act: -0.1700
Data Index: 3392359 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.5673. Min Act: -0.1700
Data Index: 3583609 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.5048. Min Act: -0.1700
Data Index: 2863976 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0673. Min Range: -6.0673
Max Act: 5.5360. Min Act: -0.1700
Data Index: 2330915 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19