Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 987 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0751. Min Range: -6.0751
Max Act: 6.0751. Min Act: -0.1700
Data Index: 869399 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.8563. Min Act: -0.1700
Data Index: 3516655 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.8563. Min Act: -0.1700
Data Index: 776950 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.8251. Min Act: -0.1700
Data Index: 7524378 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.8563. Min Act: -0.1700
Data Index: 3134582 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.7938. Min Act: -0.1700
Data Index: 1671112 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.7938. Min Act: -0.1700
Data Index: 1696295 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.7626. Min Act: -0.1700
Data Index: 5077499 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.7626. Min Act: -0.1700
Data Index: 2800046 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.7313. Min Act: -0.1700
Data Index: 1200841 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.7313. Min Act: -0.1700
Data Index: 8080390 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.7313. Min Act: -0.1700
Data Index: 1076787 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.7001. Min Act: -0.1700
Data Index: 1026906 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.7626. Min Act: -0.1700
Data Index: 7798307 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.7001. Min Act: -0.1700
Data Index: 2370306 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.7001. Min Act: -0.1700
Data Index: 8577291 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.6688. Min Act: -0.1700
Data Index: 5738728 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.6688. Min Act: -0.1700
Data Index: 2901227 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.6688. Min Act: -0.1700
Data Index: 7773876 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0751. Min Range: -6.0751
Max Act: 5.6688. Min Act: -0.1700
Data Index: 8350460 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19