Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6218 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5673. Min Range: -4.5673
Max Act: 4.5673. Min Act: -0.1700
Data Index: 1472779 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5673. Min Range: -4.5673
Max Act: 4.2235. Min Act: -0.1700
Data Index: 2066648 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5673. Min Range: -4.5673
Max Act: 4.2548. Min Act: -0.1700
Data Index: 2660042 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5673. Min Range: -4.5673
Max Act: 4.2235. Min Act: -0.1700
Data Index: 3041766 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5673. Min Range: -4.5673
Max Act: 4.1923. Min Act: -0.1700
Data Index: 7015734 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5673. Min Range: -4.5673
Max Act: 4.1923. Min Act: -0.1700
Data Index: 8412895 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5673. Min Range: -4.5673
Max Act: 4.0673. Min Act: -0.1700
Data Index: 6285150 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5673. Min Range: -4.5673
Max Act: 4.0047. Min Act: -0.1700
Data Index: 4545649 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5673. Min Range: -4.5673
Max Act: 4.0360. Min Act: -0.1700
Data Index: 6228389 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5673. Min Range: -4.5673
Max Act: 3.9735. Min Act: -0.1700
Data Index: 1540903 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5673. Min Range: -4.5673
Max Act: 3.9422. Min Act: -0.1700
Data Index: 834478 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5673. Min Range: -4.5673
Max Act: 3.9422. Min Act: -0.1700
Data Index: 2782207 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5673. Min Range: -4.5673
Max Act: 3.9109. Min Act: -0.1700
Data Index: 893997 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5673. Min Range: -4.5673
Max Act: 3.9109. Min Act: -0.1700
Data Index: 2854113 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5673. Min Range: -4.5673
Max Act: 3.9109. Min Act: -0.1700
Data Index: 4433824 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5673. Min Range: -4.5673
Max Act: 3.8484. Min Act: -0.1700
Data Index: 7212862 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5673. Min Range: -4.5673
Max Act: 3.8640. Min Act: -0.1700
Data Index: 5329673 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5673. Min Range: -4.5673
Max Act: 3.8484. Min Act: -0.1700
Data Index: 7856874 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5673. Min Range: -4.5673
Max Act: 3.8484. Min Act: -0.1700
Data Index: 579907 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5673. Min Range: -4.5673
Max Act: 3.8328. Min Act: -0.1700
Data Index: 1506577 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19