Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4965 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1863. Min Range: -7.1863
Max Act: 7.1863. Min Act: -0.1700
Data Index: 17685 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1863. Min Range: -7.1863
Max Act: 7.1863. Min Act: -0.1700
Data Index: 7872086 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1863. Min Range: -7.1863
Max Act: 7.0613. Min Act: -0.1700
Data Index: 1354201 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.9363. Min Act: -0.1700
Data Index: 6632999 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.9363. Min Act: -0.1700
Data Index: 1921540 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.9051. Min Act: -0.1700
Data Index: 1637631 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.8738. Min Act: -0.1700
Data Index: 2179147 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.8426. Min Act: -0.1700
Data Index: 8044892 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.7801. Min Act: -0.1700
Data Index: 529988 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.7801. Min Act: -0.1700
Data Index: 3617632 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.7488. Min Act: -0.1700
Data Index: 6710207 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.7488. Min Act: -0.1700
Data Index: 6368422 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.7488. Min Act: -0.1700
Data Index: 4153791 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.6551. Min Act: -0.1700
Data Index: 8429598 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.7176. Min Act: -0.1700
Data Index: 263877 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.6863. Min Act: -0.1700
Data Index: 5362795 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.6551. Min Act: -0.1700
Data Index: 1325928 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.6238. Min Act: -0.1700
Data Index: 6814844 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.5926. Min Act: -0.1700
Data Index: 4958660 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1863. Min Range: -7.1863
Max Act: 6.5926. Min Act: -0.1700
Data Index: 22990 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19