Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 807 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.5801. Min Act: -0.1700
Data Index: 7363143 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.3926. Min Act: -0.1700
Data Index: 5547759 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.3301. Min Act: -0.1700
Data Index: 2233791 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2676. Min Act: -0.1700
Data Index: 5206182 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2363. Min Act: -0.1700
Data Index: 7167165 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2676. Min Act: -0.1700
Data Index: 5569796 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2676. Min Act: -0.1700
Data Index: 4799803 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2363. Min Act: -0.1700
Data Index: 635866 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1738. Min Act: -0.1700
Data Index: 6659585 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2363. Min Act: -0.1700
Data Index: 4799801 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2051. Min Act: -0.1700
Data Index: 7774861 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1738. Min Act: -0.1700
Data Index: 4307020 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.2051. Min Act: -0.1700
Data Index: 2004736 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1426. Min Act: -0.1700
Data Index: 1744489 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1738. Min Act: -0.1700
Data Index: 2160005 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1113. Min Act: -0.1700
Data Index: 2139224 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1113. Min Act: -0.1700
Data Index: 4369743 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.1113. Min Act: -0.1700
Data Index: 5831450 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.0801. Min Act: -0.1700
Data Index: 2302646 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5801. Min Range: -6.5801
Max Act: 6.0801. Min Act: -0.1700
Data Index: 3054351 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19