Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3227 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5405. Min Range: -8.5405
Max Act: 8.5405. Min Act: -0.1700
Data Index: 7380489 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5405. Min Range: -8.5405
Max Act: 8.2905. Min Act: -0.1700
Data Index: 5155579 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5405. Min Range: -8.5405
Max Act: 8.2280. Min Act: -0.1700
Data Index: 4040093 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5405. Min Range: -8.5405
Max Act: 8.1030. Min Act: -0.1700
Data Index: 4040078 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5405. Min Range: -8.5405
Max Act: 8.1655. Min Act: -0.1700
Data Index: 4040099 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5405. Min Range: -8.5405
Max Act: 8.1030. Min Act: -0.1700
Data Index: 4040077 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5405. Min Range: -8.5405
Max Act: 8.0405. Min Act: -0.1700
Data Index: 7109813 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5405. Min Range: -8.5405
Max Act: 8.0092. Min Act: -0.1700
Data Index: 1801361 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5405. Min Range: -8.5405
Max Act: 8.0405. Min Act: -0.1700
Data Index: 4040102 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5405. Min Range: -8.5405
Max Act: 8.0405. Min Act: -0.1700
Data Index: 4040081 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5405. Min Range: -8.5405
Max Act: 8.0092. Min Act: -0.1700
Data Index: 1483576 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5405. Min Range: -8.5405
Max Act: 7.9780. Min Act: -0.1700
Data Index: 414701 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5405. Min Range: -8.5405
Max Act: 7.9780. Min Act: -0.1700
Data Index: 4040090 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5405. Min Range: -8.5405
Max Act: 7.9155. Min Act: -0.1700
Data Index: 7312838 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5405. Min Range: -8.5405
Max Act: 7.9155. Min Act: -0.1700
Data Index: 6629289 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5405. Min Range: -8.5405
Max Act: 7.9155. Min Act: -0.1700
Data Index: 8178299 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5405. Min Range: -8.5405
Max Act: 7.9155. Min Act: -0.1700
Data Index: 4536629 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5405. Min Range: -8.5405
Max Act: 7.8842. Min Act: -0.1700
Data Index: 4462910 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5405. Min Range: -8.5405
Max Act: 7.8530. Min Act: -0.1700
Data Index: 7549145 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5405. Min Range: -8.5405
Max Act: 7.8530. Min Act: -0.1700
Data Index: 6821006 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19