Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2750 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4972. Min Range: -8.4972
Max Act: 8.4972. Min Act: -0.1700
Data Index: 1955563 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4972. Min Range: -8.4972
Max Act: 8.4972. Min Act: -0.1700
Data Index: 5006677 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4972. Min Range: -8.4972
Max Act: 8.1222. Min Act: -0.1700
Data Index: 2854835 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4972. Min Range: -8.4972
Max Act: 8.0597. Min Act: -0.1700
Data Index: 3558821 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.9972. Min Act: -0.1700
Data Index: 433130 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.9972. Min Act: -0.1700
Data Index: 4931000 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.9972. Min Act: -0.1700
Data Index: 7422778 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.9972. Min Act: -0.1700
Data Index: 3990787 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.9972. Min Act: -0.1700
Data Index: 7083921 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.9972. Min Act: -0.1700
Data Index: 6988643 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.9347. Min Act: -0.1700
Data Index: 3354071 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.8097. Min Act: -0.1700
Data Index: 2673889 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.8722. Min Act: -0.1700
Data Index: 2635641 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.8722. Min Act: -0.1700
Data Index: 8657021 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.8097. Min Act: -0.1700
Data Index: 5930858 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.8097. Min Act: -0.1700
Data Index: 7723493 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.8097. Min Act: -0.1700
Data Index: 3115907 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.8097. Min Act: -0.1700
Data Index: 5422051 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.8097. Min Act: -0.1700
Data Index: 1143153 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4972. Min Range: -8.4972
Max Act: 7.8097. Min Act: -0.1700
Data Index: 7228007 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19