Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.8738. Min Act: -0.1700
Data Index: 5315100 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.7801. Min Act: -0.1700
Data Index: 8395447 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.6551. Min Act: -0.1700
Data Index: 166877 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.6238. Min Act: -0.1700
Data Index: 6762292 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.5926. Min Act: -0.1700
Data Index: 3464812 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.5613. Min Act: -0.1700
Data Index: 1448987 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4988. Min Act: -0.1700
Data Index: 5831645 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4988. Min Act: -0.1700
Data Index: 7887284 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4676. Min Act: -0.1700
Data Index: 7391044 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4676. Min Act: -0.1700
Data Index: 7739085 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4676. Min Act: -0.1700
Data Index: 7074727 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4363. Min Act: -0.1700
Data Index: 5631787 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4363. Min Act: -0.1700
Data Index: 6833518 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4363. Min Act: -0.1700
Data Index: 2577860 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4363. Min Act: -0.1700
Data Index: 8318571 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4363. Min Act: -0.1700
Data Index: 7405677 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4051. Min Act: -0.1700
Data Index: 939627 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.3738. Min Act: -0.1700
Data Index: 7216230 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.4051. Min Act: -0.1700
Data Index: 6010948 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8738. Min Range: -6.8738
Max Act: 6.3738. Min Act: -0.1700
Data Index: 7239253 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19