Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2998. Min Range: -6.2998
Max Act: 6.2998. Min Act: -0.1700
Data Index: 1737176 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2998. Min Range: -6.2998
Max Act: 6.2373. Min Act: -0.1700
Data Index: 4258705 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2998. Min Range: -6.2998
Max Act: 6.1123. Min Act: -0.1700
Data Index: 4623069 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2998. Min Range: -6.2998
Max Act: 6.0811. Min Act: -0.1700
Data Index: 6298909 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2998. Min Range: -6.2998
Max Act: 6.0186. Min Act: -0.1700
Data Index: 620475 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2998. Min Range: -6.2998
Max Act: 6.0498. Min Act: -0.1700
Data Index: 598355 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.9873. Min Act: -0.1700
Data Index: 6514011 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.8936. Min Act: -0.1700
Data Index: 1947556 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.8311. Min Act: -0.1700
Data Index: 5061550 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.8311. Min Act: -0.1700
Data Index: 3102255 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.7998. Min Act: -0.1700
Data Index: 6729816 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.7686. Min Act: -0.1700
Data Index: 289715 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.7373. Min Act: -0.1700
Data Index: 5174822 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.7373. Min Act: -0.1700
Data Index: 355102 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.6748. Min Act: -0.1700
Data Index: 4588876 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.7061. Min Act: -0.1700
Data Index: 1113905 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.6436. Min Act: -0.1700
Data Index: 156460 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.6436. Min Act: -0.1700
Data Index: 4621829 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.6123. Min Act: -0.1700
Data Index: 4203497 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2998. Min Range: -6.2998
Max Act: 5.6123. Min Act: -0.1700
Data Index: 7216655 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19