Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2075 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.6509. Min Act: -0.1700
Data Index: 1696687 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.6509. Min Act: -0.1700
Data Index: 2019512 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.4947. Min Act: -0.1700
Data Index: 6952260 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.4947. Min Act: -0.1700
Data Index: 7527098 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.4947. Min Act: -0.1700
Data Index: 2288051 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.4634. Min Act: -0.1700
Data Index: 7824801 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.4634. Min Act: -0.1700
Data Index: 8111168 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.4009. Min Act: -0.1700
Data Index: 2098420 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.4322. Min Act: -0.1700
Data Index: 6454377 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.4009. Min Act: -0.1700
Data Index: 1018736 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.3697. Min Act: -0.1700
Data Index: 3422794 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.3697. Min Act: -0.1700
Data Index: 967524 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.4009. Min Act: -0.1700
Data Index: 2695401 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.3384. Min Act: -0.1700
Data Index: 2029902 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.3384. Min Act: -0.1700
Data Index: 8181275 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.3072. Min Act: -0.1700
Data Index: 5309233 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.3072. Min Act: -0.1700
Data Index: 5782067 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.3072. Min Act: -0.1700
Data Index: 4275003 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.3072. Min Act: -0.1700
Data Index: 666420 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.2759. Min Act: -0.1700
Data Index: 525769 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19