Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.7745. Min Act: -0.1700
Data Index: 3766151 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.7432. Min Act: -0.1700
Data Index: 4407800 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.7432. Min Act: -0.1700
Data Index: 8694144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.7119. Min Act: -0.1700
Data Index: 7312560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6806. Min Act: -0.1700
Data Index: 6933496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6806. Min Act: -0.1700
Data Index: 2714874 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6806. Min Act: -0.1700
Data Index: 8108643 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6806. Min Act: -0.1700
Data Index: 1830197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6806. Min Act: -0.1700
Data Index: 1969925 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6806. Min Act: -0.1700
Data Index: 4206984 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6493. Min Act: -0.1700
Data Index: 591485 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6493. Min Act: -0.1700
Data Index: 4184465 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6180. Min Act: -0.1700
Data Index: 5582447 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6180. Min Act: -0.1700
Data Index: 1910709 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6180. Min Act: -0.1700
Data Index: 5415082 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6180. Min Act: -0.1700
Data Index: 7473038 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.5867. Min Act: -0.1700
Data Index: 78280 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.5867. Min Act: -0.1700
Data Index: 3147849 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.6180. Min Act: -0.1700
Data Index: 2156398 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7745. Min Range: -3.7745
Max Act: 3.5867. Min Act: -0.1700
Data Index: 976928 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19