Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4203 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2972. Min Range: -8.2972
Max Act: 8.2347. Min Act: -0.1700
Data Index: 5647261 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2972. Min Range: -8.2972
Max Act: 8.2972. Min Act: -0.1700
Data Index: 6945152 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2972. Min Range: -8.2972
Max Act: 8.2972. Min Act: -0.1700
Data Index: 7710205 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2972. Min Range: -8.2972
Max Act: 8.1097. Min Act: -0.1700
Data Index: 5045126 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.9847. Min Act: -0.1700
Data Index: 8353456 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.9847. Min Act: -0.1700
Data Index: 6706805 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.9847. Min Act: -0.1700
Data Index: 5954536 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.9847. Min Act: -0.1700
Data Index: 843919 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.9222. Min Act: -0.1700
Data Index: 8208535 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.9222. Min Act: -0.1700
Data Index: 7191506 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.8597. Min Act: -0.1700
Data Index: 5237585 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.8597. Min Act: -0.1700
Data Index: 8251972 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.7972. Min Act: -0.1700
Data Index: 272509 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.7972. Min Act: -0.1700
Data Index: 4016387 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.7972. Min Act: -0.1700
Data Index: 5143970 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.7972. Min Act: -0.1700
Data Index: 207506 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.7972. Min Act: -0.1700
Data Index: 2847601 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.7972. Min Act: -0.1700
Data Index: 3358304 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.7972. Min Act: -0.1700
Data Index: 8607434 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2972. Min Range: -8.2972
Max Act: 7.7347. Min Act: -0.1700
Data Index: 4583592 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19