Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3535 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.2389. Min Act: -0.1700
Data Index: 476736 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.1452. Min Act: -0.1700
Data Index: 5613466 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.1452. Min Act: -0.1700
Data Index: 5614256 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.1139. Min Act: -0.1700
Data Index: 5434990 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.0827. Min Act: -0.1700
Data Index: 6315534 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.0514. Min Act: -0.1700
Data Index: 3863919 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.0514. Min Act: -0.1700
Data Index: 853291 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.0514. Min Act: -0.1700
Data Index: 2421756 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.0201. Min Act: -0.1700
Data Index: 6602960 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.0201. Min Act: -0.1700
Data Index: 3774667 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.0201. Min Act: -0.1700
Data Index: 481934 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.0201. Min Act: -0.1700
Data Index: 18477 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.0201. Min Act: -0.1700
Data Index: 3542301 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.0201. Min Act: -0.1700
Data Index: 2328528 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2389. Min Range: -4.2389
Max Act: 3.9889. Min Act: -0.1700
Data Index: 818920 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2389. Min Range: -4.2389
Max Act: 3.9889. Min Act: -0.1700
Data Index: 6576846 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2389. Min Range: -4.2389
Max Act: 3.9889. Min Act: -0.1700
Data Index: 2319814 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2389. Min Range: -4.2389
Max Act: 3.9889. Min Act: -0.1700
Data Index: 1473683 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2389. Min Range: -4.2389
Max Act: 3.9889. Min Act: -0.1700
Data Index: 2078589 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2389. Min Range: -4.2389
Max Act: 4.0201. Min Act: -0.1700
Data Index: 4661872 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19