Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.8081. Min Act: -0.1700
Data Index: 3832403 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.6519. Min Act: -0.1700
Data Index: 6004959 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.5894. Min Act: -0.1700
Data Index: 688444 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.5894. Min Act: -0.1700
Data Index: 2253100 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.5581. Min Act: -0.1700
Data Index: 2107554 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.5269. Min Act: -0.1700
Data Index: 1621164 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.5581. Min Act: -0.1700
Data Index: 3609720 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.5269. Min Act: -0.1700
Data Index: 1693373 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.4956. Min Act: -0.1700
Data Index: 1939720 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.4644. Min Act: -0.1700
Data Index: 8245591 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.4331. Min Act: -0.1700
Data Index: 2996291 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.4331. Min Act: -0.1700
Data Index: 4637989 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.3706. Min Act: -0.1700
Data Index: 342381 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.3706. Min Act: -0.1700
Data Index: 1793152 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.3706. Min Act: -0.1700
Data Index: 6693432 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.3706. Min Act: -0.1700
Data Index: 5732046 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.3394. Min Act: -0.1700
Data Index: 1865255 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.3394. Min Act: -0.1700
Data Index: 1731914 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.3394. Min Act: -0.1700
Data Index: 6969078 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8081. Min Range: -5.8081
Max Act: 5.3081. Min Act: -0.1700
Data Index: 4451093 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19