Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.6291. Min Act: -0.1700
Data Index: 2702609 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.6291. Min Act: -0.1700
Data Index: 6955 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.6291. Min Act: -0.1700
Data Index: 5184618 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.6604. Min Act: -0.1700
Data Index: 3651671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.6291. Min Act: -0.1700
Data Index: 596697 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.6291. Min Act: -0.1700
Data Index: 6104471 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5978. Min Act: -0.1700
Data Index: 4573398 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5978. Min Act: -0.1700
Data Index: 6934126 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5978. Min Act: -0.1700
Data Index: 6426470 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5978. Min Act: -0.1700
Data Index: 8640961 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5978. Min Act: -0.1700
Data Index: 479768 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5978. Min Act: -0.1700
Data Index: 8551430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5978. Min Act: -0.1700
Data Index: 1839377 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5978. Min Act: -0.1700
Data Index: 8279614 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5665. Min Act: -0.1700
Data Index: 2886386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5665. Min Act: -0.1700
Data Index: 198353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5665. Min Act: -0.1700
Data Index: 201893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5665. Min Act: -0.1700
Data Index: 5483182 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5978. Min Act: -0.1700
Data Index: 1131155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6604. Min Range: -3.6604
Max Act: 3.5665. Min Act: -0.1700
Data Index: 1365730 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19