Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3928 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.8544. Min Act: -0.1700
Data Index: 7403760 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.8544. Min Act: -0.1700
Data Index: 260406 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.3544. Min Act: -0.1700
Data Index: 6537397 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.3544. Min Act: -0.1700
Data Index: 5154659 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.3544. Min Act: -0.1700
Data Index: 2980073 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.2919. Min Act: -0.1700
Data Index: 1137111 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.2919. Min Act: -0.1700
Data Index: 4043429 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.2294. Min Act: -0.1700
Data Index: 8224676 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.1669. Min Act: -0.1700
Data Index: 625690 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.1669. Min Act: -0.1700
Data Index: 3967729 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.1669. Min Act: -0.1700
Data Index: 7698431 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.2294. Min Act: -0.1700
Data Index: 4147948 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.2294. Min Act: -0.1700
Data Index: 2493565 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.1669. Min Act: -0.1700
Data Index: 3835815 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.1669. Min Act: -0.1700
Data Index: 3132304 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.1669. Min Act: -0.1700
Data Index: 4091668 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.1669. Min Act: -0.1700
Data Index: 1865056 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.1044. Min Act: -0.1700
Data Index: 2392734 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.1044. Min Act: -0.1700
Data Index: 476499 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8544. Min Range: -8.8544
Max Act: 8.1044. Min Act: -0.1700
Data Index: 181368 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19