Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1325 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3972. Min Range: -5.3972
Max Act: 5.3972. Min Act: -0.1700
Data Index: 3582764 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3972. Min Range: -5.3972
Max Act: 5.3660. Min Act: -0.1700
Data Index: 6794981 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3972. Min Range: -5.3972
Max Act: 5.1785. Min Act: -0.1700
Data Index: 4765423 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3972. Min Range: -5.3972
Max Act: 5.0847. Min Act: -0.1700
Data Index: 7033562 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.9597. Min Act: -0.1700
Data Index: 1277006 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.9285. Min Act: -0.1700
Data Index: 4763608 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.9597. Min Act: -0.1700
Data Index: 1086290 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.9285. Min Act: -0.1700
Data Index: 3404418 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.9597. Min Act: -0.1700
Data Index: 7214233 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.9597. Min Act: -0.1700
Data Index: 725229 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.9285. Min Act: -0.1700
Data Index: 1719110 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.9285. Min Act: -0.1700
Data Index: 8028170 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.8972. Min Act: -0.1700
Data Index: 5791891 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.8972. Min Act: -0.1700
Data Index: 5415445 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.7722. Min Act: -0.1700
Data Index: 787928 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.8035. Min Act: -0.1700
Data Index: 5003884 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.8035. Min Act: -0.1700
Data Index: 6982833 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.8035. Min Act: -0.1700
Data Index: 3529605 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.7722. Min Act: -0.1700
Data Index: 2573292 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3972. Min Range: -5.3972
Max Act: 4.7722. Min Act: -0.1700
Data Index: 8685650 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19