Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4575 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.6793. Min Act: -0.1700
Data Index: 4713514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.6480. Min Act: -0.1700
Data Index: 164430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.6480. Min Act: -0.1700
Data Index: 2262730 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.6167. Min Act: -0.1700
Data Index: 747858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.6480. Min Act: -0.1700
Data Index: 6497743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.6167. Min Act: -0.1700
Data Index: 203379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.5854. Min Act: -0.1700
Data Index: 1912576 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.6167. Min Act: -0.1700
Data Index: 647648 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.6167. Min Act: -0.1700
Data Index: 2427734 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.5854. Min Act: -0.1700
Data Index: 3504356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.6167. Min Act: -0.1700
Data Index: 2929889 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.5854. Min Act: -0.1700
Data Index: 3800329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.6167. Min Act: -0.1700
Data Index: 2737494 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.5854. Min Act: -0.1700
Data Index: 3992380 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.5854. Min Act: -0.1700
Data Index: 2989036 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.5854. Min Act: -0.1700
Data Index: 4253319 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.5854. Min Act: -0.1700
Data Index: 169515 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.5854. Min Act: -0.1700
Data Index: 1405229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.5854. Min Act: -0.1700
Data Index: 825419 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6793. Min Range: -3.6793
Max Act: 3.5854. Min Act: -0.1700
Data Index: 3482612 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19