Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.8928. Min Act: -0.1700
Data Index: 8493890 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.6116. Min Act: -0.1700
Data Index: 4328163 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.5178. Min Act: -0.1700
Data Index: 691415 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.4866. Min Act: -0.1700
Data Index: 6077898 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.4553. Min Act: -0.1700
Data Index: 6827794 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.4241. Min Act: -0.1700
Data Index: 6447989 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.3928. Min Act: -0.1700
Data Index: 5350553 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.4241. Min Act: -0.1700
Data Index: 7847218 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.3616. Min Act: -0.1700
Data Index: 7860341 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.3616. Min Act: -0.1700
Data Index: 2377714 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.3303. Min Act: -0.1700
Data Index: 2022692 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.3303. Min Act: -0.1700
Data Index: 2059895 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.2991. Min Act: -0.1700
Data Index: 1171361 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.2991. Min Act: -0.1700
Data Index: 8203880 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.2366. Min Act: -0.1700
Data Index: 5445304 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.2053. Min Act: -0.1700
Data Index: 6956937 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.2053. Min Act: -0.1700
Data Index: 3431877 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.1741. Min Act: -0.1700
Data Index: 1265432 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.2053. Min Act: -0.1700
Data Index: 4405803 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8928. Min Range: -6.8928
Max Act: 6.1741. Min Act: -0.1700
Data Index: 3631953 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19