Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2111 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.5673. Min Act: -0.1700
Data Index: 2060483 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.2548. Min Act: -0.1700
Data Index: 4423836 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.2236. Min Act: -0.1700
Data Index: 4485813 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.1923. Min Act: -0.1700
Data Index: 3588487 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.1298. Min Act: -0.1700
Data Index: 4071805 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.1611. Min Act: -0.1700
Data Index: 6025559 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.0986. Min Act: -0.1700
Data Index: 5789655 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.0986. Min Act: -0.1700
Data Index: 4659800 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.0986. Min Act: -0.1700
Data Index: 7952033 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.0986. Min Act: -0.1700
Data Index: 814325 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.0986. Min Act: -0.1700
Data Index: 3465789 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.0673. Min Act: -0.1700
Data Index: 5887 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.0361. Min Act: -0.1700
Data Index: 4242943 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.0048. Min Act: -0.1700
Data Index: 4423839 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.0048. Min Act: -0.1700
Data Index: 6825814 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.0048. Min Act: -0.1700
Data Index: 8433638 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5673. Min Range: -6.5673
Max Act: 5.9736. Min Act: -0.1700
Data Index: 4106389 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5673. Min Range: -6.5673
Max Act: 5.9736. Min Act: -0.1700
Data Index: 7162218 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5673. Min Range: -6.5673
Max Act: 5.9423. Min Act: -0.1700
Data Index: 85295 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5673. Min Range: -6.5673
Max Act: 5.9423. Min Act: -0.1700
Data Index: 4791759 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19