Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1476 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0467. Min Range: -5.0467
Max Act: 5.0467. Min Act: -0.1700
Data Index: 499630 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0467. Min Range: -5.0467
Max Act: 5.0467. Min Act: -0.1700
Data Index: 5759493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0467. Min Range: -5.0467
Max Act: 5.0155. Min Act: -0.1700
Data Index: 7162146 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9842. Min Act: -0.1700
Data Index: 3774547 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0467. Min Range: -5.0467
Max Act: 5.0155. Min Act: -0.1700
Data Index: 7793450 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9842. Min Act: -0.1699
Data Index: 5325718 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9842. Min Act: -0.1700
Data Index: 4658895 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9842. Min Act: -0.1700
Data Index: 4584708 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9842. Min Act: -0.1700
Data Index: 4130092 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9842. Min Act: -0.1700
Data Index: 6431617 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9842. Min Act: -0.1700
Data Index: 1097200 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9530. Min Act: -0.1692
Data Index: 5012967 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9530. Min Act: -0.1700
Data Index: 4199430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9530. Min Act: -0.1700
Data Index: 3592066 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9530. Min Act: -0.1700
Data Index: 8026736 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9530. Min Act: -0.1691
Data Index: 232379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9217. Min Act: -0.1700
Data Index: 1486908 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9217. Min Act: -0.1700
Data Index: 6810373 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9217. Min Act: -0.1699
Data Index: 6990417 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0467. Min Range: -5.0467
Max Act: 4.9530. Min Act: -0.1700
Data Index: 3383030 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19