Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.2130. Min Act: -0.1700
Data Index: 4182152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.2130. Min Act: -0.1700
Data Index: 5600480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.2130. Min Act: -0.1700
Data Index: 159356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.2130. Min Act: -0.1700
Data Index: 4298397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.2130. Min Act: -0.1700
Data Index: 106640 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.2130. Min Act: -0.1700
Data Index: 7254711 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.2130. Min Act: -0.1700
Data Index: 4941701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 3551278 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.2130. Min Act: -0.1700
Data Index: 3781428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 5335526 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 3589515 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 5134263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 2931869 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 1537031 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 928370 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 3532253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 3446228 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 2661936 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 4074030 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2130. Min Range: -4.2130
Max Act: 4.1818. Min Act: -0.1700
Data Index: 1437604 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19