Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2222 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0685. Min Range: -7.0685
Max Act: 7.0685. Min Act: -0.1700
Data Index: 8231163 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.8810. Min Act: -0.1700
Data Index: 818259 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.6935. Min Act: -0.1700
Data Index: 3866401 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.6623. Min Act: -0.1700
Data Index: 552047 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.5685. Min Act: -0.1700
Data Index: 4146458 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.5060. Min Act: -0.1700
Data Index: 3816294 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.5060. Min Act: -0.1700
Data Index: 6499227 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.4435. Min Act: -0.1700
Data Index: 7060393 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.4435. Min Act: -0.1700
Data Index: 2620007 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.4748. Min Act: -0.1700
Data Index: 6503266 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.4435. Min Act: -0.1700
Data Index: 5945598 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.3810. Min Act: -0.1700
Data Index: 3521377 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.3498. Min Act: -0.1700
Data Index: 7999217 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.4123. Min Act: -0.1700
Data Index: 667965 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.3498. Min Act: -0.1700
Data Index: 2267047 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.3498. Min Act: -0.1700
Data Index: 375294 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.3185. Min Act: -0.1700
Data Index: 6857699 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.3185. Min Act: -0.1700
Data Index: 7511779 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.2873. Min Act: -0.1700
Data Index: 7839855 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0685. Min Range: -7.0685
Max Act: 6.2873. Min Act: -0.1700
Data Index: 21826 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19