Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.2642. Min Act: -0.1700
Data Index: 6224528 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.2329. Min Act: -0.1700
Data Index: 363990 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.2329. Min Act: -0.1700
Data Index: 1706939 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.2329. Min Act: -0.1700
Data Index: 6915580 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.2016. Min Act: -0.1700
Data Index: 8425622 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1704. Min Act: -0.1700
Data Index: 246617 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1704. Min Act: -0.1700
Data Index: 1616483 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1704. Min Act: -0.1700
Data Index: 4763634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1704. Min Act: -0.1700
Data Index: 3032937 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1391. Min Act: -0.1700
Data Index: 3795611 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1391. Min Act: -0.1700
Data Index: 971379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1391. Min Act: -0.1700
Data Index: 8045246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1391. Min Act: -0.1700
Data Index: 763871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1391. Min Act: -0.1700
Data Index: 1664097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1391. Min Act: -0.1700
Data Index: 5836900 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1391. Min Act: -0.1700
Data Index: 419695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1704. Min Act: -0.1700
Data Index: 677919 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1079. Min Act: -0.1700
Data Index: 2683645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.1079. Min Act: -0.1700
Data Index: 1013531 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2642. Min Range: -4.2642
Max Act: 4.0766. Min Act: -0.1700
Data Index: 3268070 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19