Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1959 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.2353. Min Act: -0.1700
Data Index: 1685697 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.2040. Min Act: -0.1700
Data Index: 3769192 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.2040. Min Act: -0.1700
Data Index: 8363816 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.2040. Min Act: -0.1700
Data Index: 6483057 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.2040. Min Act: -0.1700
Data Index: 5989862 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.2040. Min Act: -0.1700
Data Index: 5415033 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.2040. Min Act: -0.1700
Data Index: 4914604 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 4266598 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1415. Min Act: -0.1700
Data Index: 4453511 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 2107495 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 456858 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 1489442 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1415. Min Act: -0.1700
Data Index: 7598178 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 1075617 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1415. Min Act: -0.1700
Data Index: 8603844 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 8725388 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 281719 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1415. Min Act: -0.1700
Data Index: 2977304 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1103. Min Act: -0.1700
Data Index: 2991952 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2353. Min Range: -5.2353
Max Act: 5.1103. Min Act: -0.1700
Data Index: 3681513 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19