Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5431 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.7690. Min Act: -0.1700
Data Index: 5192333 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.7531. Min Act: -0.1700
Data Index: 5314438 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.7531. Min Act: -0.1700
Data Index: 2168585 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.7051. Min Act: -0.1700
Data Index: 7529493 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6891. Min Act: -0.1700
Data Index: 6106958 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6731. Min Act: -0.1700
Data Index: 1970815 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6731. Min Act: -0.1700
Data Index: 2008430 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6731. Min Act: -0.1700
Data Index: 5125941 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6731. Min Act: -0.1700
Data Index: 7245109 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6731. Min Act: -0.1700
Data Index: 430138 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6731. Min Act: -0.1700
Data Index: 7605301 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6571. Min Act: -0.1700
Data Index: 5410882 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6571. Min Act: -0.1700
Data Index: 5105958 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6571. Min Act: -0.1700
Data Index: 569039 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6571. Min Act: -0.1700
Data Index: 1557948 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6571. Min Act: -0.1700
Data Index: 4297045 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6410. Min Act: -0.1700
Data Index: 4750118 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6410. Min Act: -0.1700
Data Index: 1755724 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6410. Min Act: -0.1700
Data Index: 1929489 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7690. Min Range: -2.7690
Max Act: 2.6410. Min Act: -0.1700
Data Index: 109202 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19