Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.9473. Min Act: -0.1700
Data Index: 7636895 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.3223. Min Act: -0.1700
Data Index: 2227410 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.3223. Min Act: -0.1700
Data Index: 554445 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.2598. Min Act: -0.1700
Data Index: 3533244 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.1660. Min Act: -0.1700
Data Index: 1389254 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.1660. Min Act: -0.1700
Data Index: 1983355 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.1348. Min Act: -0.1700
Data Index: 2793787 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.1348. Min Act: -0.1700
Data Index: 4802581 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.1973. Min Act: -0.1700
Data Index: 1712699 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.1348. Min Act: -0.1700
Data Index: 3998511 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.1035. Min Act: -0.1700
Data Index: 8217975 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.1035. Min Act: -0.1700
Data Index: 3825662 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.1348. Min Act: -0.1700
Data Index: 8085051 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.0410. Min Act: -0.1700
Data Index: 4674534 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.0098. Min Act: -0.1700
Data Index: 2678537 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9473. Min Range: -6.9473
Max Act: 6.0098. Min Act: -0.1700
Data Index: 8218040 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9473. Min Range: -6.9473
Max Act: 5.9785. Min Act: -0.1700
Data Index: 1018585 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9473. Min Range: -6.9473
Max Act: 5.9785. Min Act: -0.1700
Data Index: 4568965 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9473. Min Range: -6.9473
Max Act: 5.9473. Min Act: -0.1700
Data Index: 5547318 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9473. Min Range: -6.9473
Max Act: 5.9473. Min Act: -0.1700
Data Index: 5422020 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19