Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4359 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.4926. Min Act: -0.1700
Data Index: 4416236 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.4301. Min Act: -0.1700
Data Index: 3895152 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.3676. Min Act: -0.1700
Data Index: 4416242 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.3676. Min Act: -0.1700
Data Index: 8609183 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.3051. Min Act: -0.1700
Data Index: 3096379 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.3051. Min Act: -0.1700
Data Index: 499497 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.3051. Min Act: -0.1700
Data Index: 6738873 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.2426. Min Act: -0.1700
Data Index: 1939277 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.2739. Min Act: -0.1700
Data Index: 4320658 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.2114. Min Act: -0.1700
Data Index: 1891166 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.2426. Min Act: -0.1700
Data Index: 3826818 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.2426. Min Act: -0.1700
Data Index: 694067 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.2426. Min Act: -0.1700
Data Index: 5601871 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.2114. Min Act: -0.1700
Data Index: 4606371 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.2426. Min Act: -0.1700
Data Index: 1891160 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.1801. Min Act: -0.1700
Data Index: 7792118 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.1801. Min Act: -0.1700
Data Index: 7938631 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.1801. Min Act: -0.1700
Data Index: 3399757 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.1801. Min Act: -0.1700
Data Index: 5328575 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4926. Min Range: -4.4926
Max Act: 4.1488. Min Act: -0.1700
Data Index: 8189833 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19