Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1765. Min Range: -7.1765
Max Act: 7.1765. Min Act: -0.1700
Data Index: 7600086 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1765. Min Range: -7.1765
Max Act: 7.1453. Min Act: -0.1700
Data Index: 3528865 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1765. Min Range: -7.1765
Max Act: 7.1140. Min Act: -0.1700
Data Index: 1002568 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1765. Min Range: -7.1765
Max Act: 7.0828. Min Act: -0.1700
Data Index: 7303789 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1765. Min Range: -7.1765
Max Act: 7.0828. Min Act: -0.1700
Data Index: 5389180 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1765. Min Range: -7.1765
Max Act: 7.0828. Min Act: -0.1700
Data Index: 910527 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1765. Min Range: -7.1765
Max Act: 7.0515. Min Act: -0.1700
Data Index: 7217677 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.9890. Min Act: -0.1700
Data Index: 8575309 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.9578. Min Act: -0.1700
Data Index: 6325885 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.9578. Min Act: -0.1700
Data Index: 79375 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.9578. Min Act: -0.1700
Data Index: 7751038 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.8640. Min Act: -0.1700
Data Index: 3531999 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.8328. Min Act: -0.1700
Data Index: 7893980 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.8328. Min Act: -0.1700
Data Index: 7175044 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.7078. Min Act: -0.1700
Data Index: 5314516 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.6453. Min Act: -0.1700
Data Index: 5230510 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.6765. Min Act: -0.1700
Data Index: 5634928 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.6140. Min Act: -0.1700
Data Index: 7071578 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.5828. Min Act: -0.1700
Data Index: 1252140 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1765. Min Range: -7.1765
Max Act: 6.5828. Min Act: -0.1700
Data Index: 3167210 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19