Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4709 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.5405. Min Act: -0.1700
Data Index: 3058377 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.3217. Min Act: -0.1700
Data Index: 4178485 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1967. Min Act: -0.1700
Data Index: 5951558 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1967. Min Act: -0.1589
Data Index: 5610956 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1655. Min Act: -0.1700
Data Index: 3167843 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1342. Min Act: -0.1700
Data Index: 3683051 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1342. Min Act: -0.1700
Data Index: 8799605 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1342. Min Act: -0.1700
Data Index: 7207182 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1030. Min Act: -0.1700
Data Index: 3450671 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1342. Min Act: -0.1700
Data Index: 7955937 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1342. Min Act: -0.1700
Data Index: 3566901 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1342. Min Act: -0.1700
Data Index: 5101250 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.0717. Min Act: -0.1696
Data Index: 6630664 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1030. Min Act: -0.1700
Data Index: 2386660 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1030. Min Act: -0.1698
Data Index: 8144054 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.1030. Min Act: -0.1700
Data Index: 1055250 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.0717. Min Act: -0.1700
Data Index: 2405866 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.0717. Min Act: -0.1700
Data Index: 2439509 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.0717. Min Act: -0.1700
Data Index: 6939975 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5405. Min Range: -5.5405
Max Act: 5.0717. Min Act: -0.1700
Data Index: 1638651 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19