Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5593 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1870. Min Range: -4.1870
Max Act: 4.1870. Min Act: -0.1700
Data Index: 1655665 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1870. Min Range: -4.1870
Max Act: 4.1245. Min Act: -0.1700
Data Index: 33618 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.9995. Min Act: -0.1700
Data Index: 1570774 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.9682. Min Act: -0.1700
Data Index: 1106166 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.9369. Min Act: -0.1700
Data Index: 1905866 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.9057. Min Act: -0.1700
Data Index: 8334566 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8744. Min Act: -0.1700
Data Index: 492420 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8744. Min Act: -0.1700
Data Index: 1405070 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8744. Min Act: -0.1700
Data Index: 1772115 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8744. Min Act: -0.1700
Data Index: 8517836 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8744. Min Act: -0.1700
Data Index: 1164889 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8431. Min Act: -0.1700
Data Index: 4936097 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8431. Min Act: -0.1700
Data Index: 5764320 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8119. Min Act: -0.1700
Data Index: 5613344 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8431. Min Act: -0.1700
Data Index: 1630453 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8431. Min Act: -0.1700
Data Index: 5313894 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8744. Min Act: -0.1700
Data Index: 5953192 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8119. Min Act: -0.1700
Data Index: 3075209 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8119. Min Act: -0.1700
Data Index: 4580429 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1870. Min Range: -4.1870
Max Act: 3.8119. Min Act: -0.1700
Data Index: 3195107 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19