Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3331. Min Range: -8.3331
Max Act: 8.3331. Min Act: -0.1700
Data Index: 3134659 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.9581. Min Act: -0.1700
Data Index: 834639 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.8331. Min Act: -0.1700
Data Index: 825174 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.8331. Min Act: -0.1700
Data Index: 1568292 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.7706. Min Act: -0.1700
Data Index: 4429353 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.7706. Min Act: -0.1700
Data Index: 1209891 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.7706. Min Act: -0.1700
Data Index: 4137307 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.7081. Min Act: -0.1700
Data Index: 3718253 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.7081. Min Act: -0.1700
Data Index: 6259283 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.7081. Min Act: -0.1700
Data Index: 774431 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.5831. Min Act: -0.1700
Data Index: 788829 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.5831. Min Act: -0.1700
Data Index: 4374793 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.5206. Min Act: -0.1700
Data Index: 1811321 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.5206. Min Act: -0.1700
Data Index: 5300713 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.5206. Min Act: -0.1700
Data Index: 1592005 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.5206. Min Act: -0.1700
Data Index: 4090518 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.4894. Min Act: -0.1700
Data Index: 6744015 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.4581. Min Act: -0.1700
Data Index: 2094375 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.4581. Min Act: -0.1700
Data Index: 695721 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3331. Min Range: -8.3331
Max Act: 7.4581. Min Act: -0.1700
Data Index: 6628853 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19