Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 397 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1029. Min Range: -8.1029
Max Act: 8.1029. Min Act: -0.1700
Data Index: 7466483 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1029. Min Range: -8.1029
Max Act: 8.0404. Min Act: -0.1700
Data Index: 4828530 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.9779. Min Act: -0.1700
Data Index: 1425129 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.9779. Min Act: -0.1700
Data Index: 6067599 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.9779. Min Act: -0.1700
Data Index: 3450063 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.9779. Min Act: -0.1700
Data Index: 35040 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.9154. Min Act: -0.1700
Data Index: 304795 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.9154. Min Act: -0.1700
Data Index: 6329994 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.8529. Min Act: -0.1700
Data Index: 1965911 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.8529. Min Act: -0.1700
Data Index: 6960482 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.8529. Min Act: -0.1700
Data Index: 7600984 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 890464 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.8529. Min Act: -0.1700
Data Index: 3176252 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 6773576 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 5802439 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 4474916 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 7088932 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 2094705 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 272980 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1029. Min Range: -8.1029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 7858722 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19