Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6000 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.7783. Min Act: -0.1700
Data Index: 1107266 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.5908. Min Act: -0.1700
Data Index: 994214 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.5283. Min Act: -0.1700
Data Index: 1610303 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.4658. Min Act: -0.1700
Data Index: 2549017 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.2783. Min Act: -0.1700
Data Index: 4101841 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.2783. Min Act: -0.1700
Data Index: 7918609 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.3408. Min Act: -0.1700
Data Index: 7553275 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.2158. Min Act: -0.1700
Data Index: 1201205 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.1533. Min Act: -0.1700
Data Index: 5373201 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.1533. Min Act: -0.1700
Data Index: 3928936 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.1533. Min Act: -0.1700
Data Index: 6552711 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.1533. Min Act: -0.1700
Data Index: 4814209 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.0908. Min Act: -0.1700
Data Index: 5218244 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.0908. Min Act: -0.1700
Data Index: 6977781 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7783. Min Range: -8.7783
Max Act: 7.9658. Min Act: -0.1700
Data Index: 1341947 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7783. Min Range: -8.7783
Max Act: 7.9658. Min Act: -0.1700
Data Index: 8357676 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7783. Min Range: -8.7783
Max Act: 7.9658. Min Act: -0.1700
Data Index: 3273727 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7783. Min Range: -8.7783
Max Act: 7.9658. Min Act: -0.1700
Data Index: 2419439 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7783. Min Range: -8.7783
Max Act: 8.0283. Min Act: -0.1700
Data Index: 7517942 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7783. Min Range: -8.7783
Max Act: 7.9033. Min Act: -0.1700
Data Index: 3833662 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19