Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3235 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.4869. Min Act: -0.1700
Data Index: 3920626 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.4869. Min Act: -0.1700
Data Index: 5430166 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.4557. Min Act: -0.1700
Data Index: 3728764 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.4244. Min Act: -0.1700
Data Index: 3428121 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.3307. Min Act: -0.1700
Data Index: 8404848 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.3307. Min Act: -0.1700
Data Index: 5216882 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.2994. Min Act: -0.1700
Data Index: 6650901 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.2682. Min Act: -0.1700
Data Index: 4408082 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.2369. Min Act: -0.1700
Data Index: 6797603 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.2369. Min Act: -0.1700
Data Index: 3013679 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.2057. Min Act: -0.1700
Data Index: 8043693 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.2057. Min Act: -0.1700
Data Index: 4097685 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.2057. Min Act: -0.1700
Data Index: 1810134 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.1744. Min Act: -0.1700
Data Index: 8696098 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.1744. Min Act: -0.1700
Data Index: 2440595 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.1744. Min Act: -0.1700
Data Index: 6391162 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.1744. Min Act: -0.1700
Data Index: 3172951 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.1119. Min Act: -0.1700
Data Index: 5106512 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.1119. Min Act: -0.1700
Data Index: 8087230 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.0807. Min Act: -0.1700
Data Index: 484038 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19