Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1616 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.6673. Min Act: -0.1700
Data Index: 8452584 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.4486. Min Act: -0.1700
Data Index: 8685980 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.4486. Min Act: -0.1700
Data Index: 3908943 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.3548. Min Act: -0.1700
Data Index: 5882823 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.2923. Min Act: -0.1700
Data Index: 3907750 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.2923. Min Act: -0.1700
Data Index: 3907749 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.2298. Min Act: -0.1700
Data Index: 6289651 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.2611. Min Act: -0.1700
Data Index: 381100 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.1986. Min Act: -0.1700
Data Index: 4601288 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.1986. Min Act: -0.1700
Data Index: 7881834 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.1361. Min Act: -0.1700
Data Index: 1540695 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.1361. Min Act: -0.1700
Data Index: 2986846 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.1361. Min Act: -0.1700
Data Index: 1596347 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.1048. Min Act: -0.1700
Data Index: 3500867 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0736. Min Act: -0.1700
Data Index: 7776763 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0111. Min Act: -0.1700
Data Index: 3151163 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0111. Min Act: -0.1700
Data Index: 4918036 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0111. Min Act: -0.1700
Data Index: 7118902 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6673. Min Range: -6.6673
Max Act: 5.9798. Min Act: -0.1700
Data Index: 8452586 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6673. Min Range: -6.6673
Max Act: 6.0111. Min Act: -0.1700
Data Index: 5345565 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19