Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1094 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6501. Min Act: -0.1700
Data Index: 1809301 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6501. Min Act: -0.1700
Data Index: 8463876 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6501. Min Act: -0.1700
Data Index: 933256 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6188. Min Act: -0.1700
Data Index: 1820834 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6188. Min Act: -0.1700
Data Index: 2722506 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6188. Min Act: -0.1700
Data Index: 3159962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6188. Min Act: -0.1700
Data Index: 3572529 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 3589138 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 8179508 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 4669138 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 7448223 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 4547717 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 206707 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 7224270 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 642464 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 6852790 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 5946765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 532005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.6031. Min Act: -0.1700
Data Index: 5539549 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6501. Min Range: -3.6501
Max Act: 3.5875. Min Act: -0.1700
Data Index: 5536758 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19