Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2799 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0788. Min Range: -6.0788
Max Act: 6.0788. Min Act: -0.1700
Data Index: 4448144 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0788. Min Range: -6.0788
Max Act: 6.0475. Min Act: -0.1700
Data Index: 4879007 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.9850. Min Act: -0.1700
Data Index: 386934 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.9850. Min Act: -0.1700
Data Index: 563767 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.9850. Min Act: -0.1700
Data Index: 2740944 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.9850. Min Act: -0.1700
Data Index: 8044057 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.9538. Min Act: -0.1700
Data Index: 6132120 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8913. Min Act: -0.1700
Data Index: 8308218 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8913. Min Act: -0.1700
Data Index: 4632042 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8913. Min Act: -0.1700
Data Index: 6647647 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8913. Min Act: -0.1700
Data Index: 7268137 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8600. Min Act: -0.1700
Data Index: 7776311 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8600. Min Act: -0.1700
Data Index: 4837185 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8288. Min Act: -0.1700
Data Index: 5118760 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8600. Min Act: -0.1700
Data Index: 8270020 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8600. Min Act: -0.1700
Data Index: 6667353 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8600. Min Act: -0.1700
Data Index: 330808 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8288. Min Act: -0.1700
Data Index: 699912 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8288. Min Act: -0.1700
Data Index: 2356522 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0788. Min Range: -6.0788
Max Act: 5.8288. Min Act: -0.1700
Data Index: 952017 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19