Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1722 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1040. Min Range: -9.1040
Max Act: 9.1040. Min Act: -0.1700
Data Index: 5543415 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1040. Min Range: -9.1040
Max Act: 9.1040. Min Act: -0.1700
Data Index: 4674706 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.9165. Min Act: -0.1700
Data Index: 6820208 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.7915. Min Act: -0.1700
Data Index: 966659 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.7915. Min Act: -0.1700
Data Index: 4633975 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.5415. Min Act: -0.1700
Data Index: 685070 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.5415. Min Act: -0.1700
Data Index: 5067581 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.5415. Min Act: -0.1700
Data Index: 4363501 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.4790. Min Act: -0.1700
Data Index: 8221542 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.4790. Min Act: -0.1700
Data Index: 8407602 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.4790. Min Act: -0.1700
Data Index: 860982 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.4790. Min Act: -0.1700
Data Index: 8549235 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.4790. Min Act: -0.1700
Data Index: 7246268 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.4165. Min Act: -0.1700
Data Index: 3374368 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.4165. Min Act: -0.1700
Data Index: 5083524 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.3540. Min Act: -0.1700
Data Index: 3157936 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.3540. Min Act: -0.1700
Data Index: 3586492 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.3540. Min Act: -0.1700
Data Index: 1047197 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.3540. Min Act: -0.1700
Data Index: 6217821 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.3540. Min Act: -0.1700
Data Index: 6652946 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19