Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6252 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.9210. Min Act: -0.1700
Data Index: 1612491 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.9052. Min Act: -0.1700
Data Index: 1089466 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8893. Min Act: -0.1700
Data Index: 8126753 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8893. Min Act: -0.1700
Data Index: 1089473 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8734. Min Act: -0.1700
Data Index: 4569092 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8734. Min Act: -0.1700
Data Index: 1840999 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8576. Min Act: -0.1700
Data Index: 4116542 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8258. Min Act: -0.1700
Data Index: 428039 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8417. Min Act: -0.1700
Data Index: 461172 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8417. Min Act: -0.1700
Data Index: 3399890 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8417. Min Act: -0.1700
Data Index: 5349202 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8417. Min Act: -0.1700
Data Index: 6229227 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8417. Min Act: -0.1700
Data Index: 1521293 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8258. Min Act: -0.1700
Data Index: 4569090 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8258. Min Act: -0.1700
Data Index: 5434467 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8258. Min Act: -0.1700
Data Index: 646118 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8258. Min Act: -0.1700
Data Index: 2417524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8258. Min Act: -0.1700
Data Index: 4427399 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8099. Min Act: -0.1700
Data Index: 2003504 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9210. Min Range: -2.9210
Max Act: 2.8099. Min Act: -0.1700
Data Index: 60349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19