Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.2710. Min Act: -0.1700
Data Index: 4828625 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.2358. Min Act: -0.1700
Data Index: 2417993 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.2358. Min Act: -0.1700
Data Index: 5457154 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.2358. Min Act: -0.1700
Data Index: 3736628 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.2358. Min Act: -0.1700
Data Index: 3740891 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.2182. Min Act: -0.1700
Data Index: 3074652 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.2182. Min Act: -0.1700
Data Index: 4906396 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.2005. Min Act: -0.1700
Data Index: 2504898 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.2005. Min Act: -0.1700
Data Index: 3129391 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.1829. Min Act: -0.1700
Data Index: 8112882 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.1829. Min Act: -0.1700
Data Index: 8332419 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.1829. Min Act: -0.1700
Data Index: 2555425 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.2005. Min Act: -0.1700
Data Index: 2220215 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.1653. Min Act: -0.1700
Data Index: 4369017 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.1653. Min Act: -0.1700
Data Index: 3075560 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.1653. Min Act: -0.1700
Data Index: 1770867 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.1653. Min Act: -0.1700
Data Index: 629843 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.1653. Min Act: -0.1700
Data Index: 4878121 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.1653. Min Act: -0.1700
Data Index: 1213736 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2710. Min Range: -1.2710
Max Act: 1.1653. Min Act: -0.1700
Data Index: 2955520 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19