Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3593 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4270. Min Range: -4.4270
Max Act: 4.4270. Min Act: -0.1700
Data Index: 7338133 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4270. Min Range: -4.4270
Max Act: 4.1457. Min Act: -0.1700
Data Index: 5949777 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4270. Min Range: -4.4270
Max Act: 4.1144. Min Act: -0.1700
Data Index: 3741864 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4270. Min Range: -4.4270
Max Act: 4.0832. Min Act: -0.1700
Data Index: 1694295 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4270. Min Range: -4.4270
Max Act: 4.0519. Min Act: -0.1700
Data Index: 3773882 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4270. Min Range: -4.4270
Max Act: 4.0207. Min Act: -0.1700
Data Index: 7262810 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4270. Min Range: -4.4270
Max Act: 4.0519. Min Act: -0.1700
Data Index: 6885046 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.9581. Min Act: -0.1700
Data Index: 7444807 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.9581. Min Act: -0.1700
Data Index: 1007462 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.9581. Min Act: -0.1700
Data Index: 5033849 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.9269. Min Act: -0.1700
Data Index: 5576869 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.9269. Min Act: -0.1700
Data Index: 5521184 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.9269. Min Act: -0.1700
Data Index: 1775606 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.8956. Min Act: -0.1700
Data Index: 4663000 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.8956. Min Act: -0.1700
Data Index: 4576303 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.8643. Min Act: -0.1700
Data Index: 1556776 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.8956. Min Act: -0.1700
Data Index: 7262140 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.8956. Min Act: -0.1700
Data Index: 6658669 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.8956. Min Act: -0.1700
Data Index: 712508 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4270. Min Range: -4.4270
Max Act: 3.8956. Min Act: -0.1700
Data Index: 6048089 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19