Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3806 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1006. Min Range: -4.1006
Max Act: 4.1006. Min Act: -0.1700
Data Index: 517033 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1006. Min Range: -4.1006
Max Act: 4.1006. Min Act: -0.1700
Data Index: 8811506 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1006. Min Range: -4.1006
Max Act: 4.0068. Min Act: -0.1700
Data Index: 4501879 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.9443. Min Act: -0.1700
Data Index: 3549271 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.9130. Min Act: -0.1700
Data Index: 4395992 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.9130. Min Act: -0.1700
Data Index: 8344587 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.9130. Min Act: -0.1700
Data Index: 1044870 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.8818. Min Act: -0.1700
Data Index: 3252371 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.8505. Min Act: -0.1700
Data Index: 8814951 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.8505. Min Act: -0.1700
Data Index: 2354020 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.7880. Min Act: -0.1700
Data Index: 8507874 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.7723. Min Act: -0.1700
Data Index: 8751548 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.7723. Min Act: -0.1700
Data Index: 82077 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.7723. Min Act: -0.1700
Data Index: 633842 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.7567. Min Act: -0.1700
Data Index: 4395993 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.7880. Min Act: -0.1700
Data Index: 3115610 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.7723. Min Act: -0.1700
Data Index: 5230119 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.7410. Min Act: -0.1700
Data Index: 7030723 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.7410. Min Act: -0.1700
Data Index: 827757 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1006. Min Range: -4.1006
Max Act: 3.7567. Min Act: -0.1700
Data Index: 1585523 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19