Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1620. Min Range: -10.1620
Max Act: 10.1620. Min Act: -0.1700
Data Index: 7045758 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.6620. Min Act: -0.1700
Data Index: 4203346 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.6620. Min Act: -0.1700
Data Index: 6287426 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.6620. Min Act: -0.1700
Data Index: 8008167 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.5370. Min Act: -0.1700
Data Index: 2027182 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.5370. Min Act: -0.1700
Data Index: 7929953 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.4745. Min Act: -0.1700
Data Index: 6192520 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.5370. Min Act: -0.1700
Data Index: 1114105 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.4120. Min Act: -0.1700
Data Index: 4283160 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.4120. Min Act: -0.1700
Data Index: 3295610 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.3495. Min Act: -0.1700
Data Index: 2388162 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.3495. Min Act: -0.1700
Data Index: 1217527 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.4120. Min Act: -0.1700
Data Index: 8364384 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.3495. Min Act: -0.1700
Data Index: 8386789 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.2870. Min Act: -0.1700
Data Index: 7584590 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.2245. Min Act: -0.1700
Data Index: 6431120 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.2245. Min Act: -0.1700
Data Index: 209069 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.2245. Min Act: -0.1700
Data Index: 2820637 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.1620. Min Act: -0.1700
Data Index: 5388920 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1620. Min Range: -10.1620
Max Act: 9.1620. Min Act: -0.1700
Data Index: 2799131 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19