Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1630 in Layer 32
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: 4192920 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.5361. Min Act: -0.1700
Data Index: 8120801 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.4736. Min Act: -0.1700
Data Index: 1337623 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.4423. Min Act: -0.1700
Data Index: 986405 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.3798. Min Act: -0.1700
Data Index: 6352988 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.3798. Min Act: -0.1700
Data Index: 5569488 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.3486. Min Act: -0.1700
Data Index: 3558009 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.3486. Min Act: -0.1700
Data Index: 4599239 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.2861. Min Act: -0.1700
Data Index: 583130 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.3486. Min Act: -0.1700
Data Index: 6529728 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.3173. Min Act: -0.1700
Data Index: 8408651 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.3486. Min Act: -0.1700
Data Index: 3061455 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.2861. Min Act: -0.1700
Data Index: 1854497 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.2861. Min Act: -0.1700
Data Index: 3543459 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.2861. Min Act: -0.1700
Data Index: 3832906 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.2548. Min Act: -0.1700
Data Index: 5384030 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.2548. Min Act: -0.1700
Data Index: 8628219 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.2861. Min Act: -0.1700
Data Index: 4522089 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.2548. Min Act: -0.1700
Data Index: 1855800 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5673. Min Range: -6.5673
Max Act: 6.1923. Min Act: -0.1700
Data Index: 6399928 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19