Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1296 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7710. Min Range: -12.7710
Max Act: 12.7710. Min Act: -0.1700
Data Index: 686114 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7710. Min Range: -12.7710
Max Act: 12.7085. Min Act: -0.1700
Data Index: 3474194 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7710. Min Range: -12.7710
Max Act: 12.7085. Min Act: -0.1700
Data Index: 7329257 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7710. Min Range: -12.7710
Max Act: 12.5835. Min Act: -0.1700
Data Index: 984564 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7710. Min Range: -12.7710
Max Act: 12.4585. Min Act: -0.1700
Data Index: 2214007 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7710. Min Range: -12.7710
Max Act: 12.0835. Min Act: -0.1700
Data Index: 5390450 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7710. Min Range: -12.7710
Max Act: 11.6460. Min Act: -0.1700
Data Index: 8662751 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.5210. Min Act: -0.1700
Data Index: 8395915 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.3335. Min Act: -0.1700
Data Index: 3747885 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.3335. Min Act: -0.1700
Data Index: 1686076 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.2710. Min Act: -0.1700
Data Index: 8405104 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.2710. Min Act: -0.1700
Data Index: 6128790 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.2710. Min Act: -0.1700
Data Index: 4654738 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.2710. Min Act: -0.1700
Data Index: 5266299 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.2085. Min Act: -0.1700
Data Index: 3280599 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.1460. Min Act: -0.1700
Data Index: 7503044 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.0210. Min Act: -0.1700
Data Index: 6050206 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.0210. Min Act: -0.1700
Data Index: 1782662 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.0210. Min Act: -0.1700
Data Index: 7179254 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7710. Min Range: -12.7710
Max Act: 10.0210. Min Act: -0.1700
Data Index: 1446198 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19