Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1927 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.4993. Min Act: -0.1700
Data Index: 1120934 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.4993. Min Act: -0.1700
Data Index: 3047012 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.4993. Min Act: -0.1700
Data Index: 1880313 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.3431. Min Act: -0.1700
Data Index: 8778494 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.2806. Min Act: -0.1700
Data Index: 2561500 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.2493. Min Act: -0.1700
Data Index: 4706777 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.2181. Min Act: -0.1700
Data Index: 365448 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.2181. Min Act: -0.1700
Data Index: 7964985 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.1868. Min Act: -0.1700
Data Index: 1852522 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.1868. Min Act: -0.1700
Data Index: 5434085 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.1556. Min Act: -0.1700
Data Index: 1810830 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.1243. Min Act: -0.1700
Data Index: 6133531 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.0931. Min Act: -0.1700
Data Index: 3609178 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.0931. Min Act: -0.1700
Data Index: 5678870 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.0618. Min Act: -0.1700
Data Index: 7156670 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.0618. Min Act: -0.1700
Data Index: 8056824 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.0931. Min Act: -0.1700
Data Index: 8165717 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.0618. Min Act: -0.1700
Data Index: 5135300 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.0306. Min Act: -0.1700
Data Index: 332550 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4993. Min Range: -5.4993
Max Act: 5.0306. Min Act: -0.1700
Data Index: 941041 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19