Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1561 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1941. Min Range: -7.1941
Max Act: 7.1941. Min Act: -0.1700
Data Index: 536929 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1941. Min Range: -7.1941
Max Act: 7.1316. Min Act: -0.1700
Data Index: 862623 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1941. Min Range: -7.1941
Max Act: 7.0691. Min Act: -0.1700
Data Index: 3961654 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1941. Min Range: -7.1941
Max Act: 7.0379. Min Act: -0.1700
Data Index: 1596779 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1941. Min Range: -7.1941
Max Act: 7.0379. Min Act: -0.1700
Data Index: 6927918 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1941. Min Range: -7.1941
Max Act: 7.0379. Min Act: -0.1700
Data Index: 905070 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1941. Min Range: -7.1941
Max Act: 7.0379. Min Act: -0.1699
Data Index: 546633 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1941. Min Range: -7.1941
Max Act: 7.0066. Min Act: -0.1700
Data Index: 8812225 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1941. Min Range: -7.1941
Max Act: 6.9441. Min Act: -0.1700
Data Index: 6994412 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1941. Min Range: -7.1941
Max Act: 7.0066. Min Act: -0.1700
Data Index: 7443024 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1941. Min Range: -7.1941
Max Act: 6.9754. Min Act: -0.1698
Data Index: 8081368 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1941. Min Range: -7.1941
Max Act: 6.9754. Min Act: -0.1700
Data Index: 5540490 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1941. Min Range: -7.1941
Max Act: 6.9754. Min Act: -0.1700
Data Index: 2717729 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1941. Min Range: -7.1941
Max Act: 6.9129. Min Act: -0.1700
Data Index: 7890319 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1941. Min Range: -7.1941
Max Act: 6.9129. Min Act: -0.1700
Data Index: 7859927 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1941. Min Range: -7.1941
Max Act: 6.9129. Min Act: -0.1700
Data Index: 7089081 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1941. Min Range: -7.1941
Max Act: 6.9129. Min Act: -0.1700
Data Index: 4001665 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1941. Min Range: -7.1941
Max Act: 6.9129. Min Act: -0.1700
Data Index: 6422561 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1941. Min Range: -7.1941
Max Act: 6.8816. Min Act: -0.1700
Data Index: 3652421 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1941. Min Range: -7.1941
Max Act: 6.9129. Min Act: -0.1700
Data Index: 6042881 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19