Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2010. Min Range: -5.2010
Max Act: 5.2010. Min Act: -0.1700
Data Index: 5364440 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2010. Min Range: -5.2010
Max Act: 5.2010. Min Act: -0.1700
Data Index: 1851676 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2010. Min Range: -5.2010
Max Act: 5.0448. Min Act: -0.1700
Data Index: 2436089 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2010. Min Range: -5.2010
Max Act: 5.0448. Min Act: -0.1700
Data Index: 2857567 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.9823. Min Act: -0.1700
Data Index: 5396669 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.9510. Min Act: -0.1700
Data Index: 5264197 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.9510. Min Act: -0.1700
Data Index: 4786285 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.9510. Min Act: -0.1700
Data Index: 95061 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.9198. Min Act: -0.1700
Data Index: 5647220 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.9198. Min Act: -0.1700
Data Index: 4683837 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.8885. Min Act: -0.1700
Data Index: 5286588 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.8885. Min Act: -0.1700
Data Index: 6025155 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.8885. Min Act: -0.1700
Data Index: 3152676 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.9198. Min Act: -0.1700
Data Index: 4519362 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.9198. Min Act: -0.1700
Data Index: 4791010 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.8573. Min Act: -0.1700
Data Index: 7813057 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.8573. Min Act: -0.1700
Data Index: 4346045 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.8573. Min Act: -0.1700
Data Index: 8713983 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.8260. Min Act: -0.1700
Data Index: 6957393 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2010. Min Range: -5.2010
Max Act: 4.8573. Min Act: -0.1700
Data Index: 1974084 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19