Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0061. Min Range: -5.0061
Max Act: 5.0061. Min Act: -0.1700
Data Index: 6326244 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.8811. Min Act: -0.1700
Data Index: 1650485 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.8498. Min Act: -0.1700
Data Index: 8183994 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.7248. Min Act: -0.1700
Data Index: 4109818 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6936. Min Act: -0.1700
Data Index: 2663511 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6936. Min Act: -0.1700
Data Index: 1476196 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6936. Min Act: -0.1700
Data Index: 369382 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6936. Min Act: -0.1700
Data Index: 1539753 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6623. Min Act: -0.1700
Data Index: 3907913 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6623. Min Act: -0.1700
Data Index: 5228012 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6311. Min Act: -0.1700
Data Index: 4272997 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6311. Min Act: -0.1700
Data Index: 2663512 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6311. Min Act: -0.1700
Data Index: 4227674 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6311. Min Act: -0.1700
Data Index: 7504382 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6311. Min Act: -0.1700
Data Index: 2198876 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6311. Min Act: -0.1700
Data Index: 2877903 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.6311. Min Act: -0.1700
Data Index: 6284671 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.5998. Min Act: -0.1700
Data Index: 6502328 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.5998. Min Act: -0.1700
Data Index: 7282181 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0061. Min Range: -5.0061
Max Act: 4.5998. Min Act: -0.1700
Data Index: 5891540 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19