Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3168 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0072. Min Range: -6.0072
Max Act: 6.0072. Min Act: -0.1700
Data Index: 3611900 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.8509. Min Act: -0.1700
Data Index: 3611896 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.8197. Min Act: -0.1700
Data Index: 7737968 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.7572. Min Act: -0.1700
Data Index: 8832394 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.7259. Min Act: -0.1700
Data Index: 318155 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.6947. Min Act: -0.1700
Data Index: 1826316 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.6634. Min Act: -0.1700
Data Index: 5432979 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.6322. Min Act: -0.1700
Data Index: 5159330 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.6322. Min Act: -0.1700
Data Index: 915543 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.6322. Min Act: -0.1700
Data Index: 2532226 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.5697. Min Act: -0.1700
Data Index: 4953830 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.6009. Min Act: -0.1700
Data Index: 5190542 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.5697. Min Act: -0.1700
Data Index: 99165 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.5384. Min Act: -0.1700
Data Index: 4631140 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.5072. Min Act: -0.1700
Data Index: 2093562 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.5072. Min Act: -0.1700
Data Index: 821501 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.5072. Min Act: -0.1700
Data Index: 6129154 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.4759. Min Act: -0.1700
Data Index: 2850519 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.4759. Min Act: -0.1700
Data Index: 3276112 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0072. Min Range: -6.0072
Max Act: 5.4759. Min Act: -0.1700
Data Index: 4631137 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19