Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2097. Min Range: -7.2097
Max Act: 7.2097. Min Act: -0.1700
Data Index: 5201821 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2097. Min Range: -7.2097
Max Act: 7.1785. Min Act: -0.1700
Data Index: 4360953 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2097. Min Range: -7.2097
Max Act: 7.1472. Min Act: -0.1700
Data Index: 1329642 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2097. Min Range: -7.2097
Max Act: 7.1472. Min Act: -0.1700
Data Index: 1694181 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2097. Min Range: -7.2097
Max Act: 7.0535. Min Act: -0.1700
Data Index: 3513028 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2097. Min Range: -7.2097
Max Act: 7.0535. Min Act: -0.1700
Data Index: 1422243 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2097. Min Range: -7.2097
Max Act: 7.0222. Min Act: -0.1700
Data Index: 7924121 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2097. Min Range: -7.2097
Max Act: 7.0222. Min Act: -0.1700
Data Index: 8060992 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2097. Min Range: -7.2097
Max Act: 7.0222. Min Act: -0.1700
Data Index: 6951857 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2097. Min Range: -7.2097
Max Act: 6.9910. Min Act: -0.1700
Data Index: 2903037 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2097. Min Range: -7.2097
Max Act: 6.9597. Min Act: -0.1700
Data Index: 712528 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2097. Min Range: -7.2097
Max Act: 6.9597. Min Act: -0.1700
Data Index: 2635359 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2097. Min Range: -7.2097
Max Act: 6.9285. Min Act: -0.1700
Data Index: 3379425 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2097. Min Range: -7.2097
Max Act: 6.9285. Min Act: -0.1700
Data Index: 5068291 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2097. Min Range: -7.2097
Max Act: 6.8972. Min Act: -0.1700
Data Index: 438366 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2097. Min Range: -7.2097
Max Act: 6.8972. Min Act: -0.1700
Data Index: 8061011 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2097. Min Range: -7.2097
Max Act: 6.8972. Min Act: -0.1700
Data Index: 4620826 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2097. Min Range: -7.2097
Max Act: 6.8972. Min Act: -0.1700
Data Index: 2971188 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2097. Min Range: -7.2097
Max Act: 6.8660. Min Act: -0.1700
Data Index: 1353773 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2097. Min Range: -7.2097
Max Act: 6.8660. Min Act: -0.1700
Data Index: 87662 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19